Research Publications - Generative AI
Select a Topic:
Our Generative AI Research
We design novel generative AI architectures that produces multi-modal outputs, including images, shapes, skeletal motion, and 3D structures, often with controllability features delivered through intuitive user interfaces.
Interested in our research? Consider joining us.
Journal Papers
On the Design Fundamentals of Diffusion Models: A Survey Impact Factor: 7.6† Top 25% Journal in Computer Science, Artificial Intelligence† Citation: 108#
Pattern Recognition (PR), 2026
Ziyi Chang, George Alex Koulieris, Hyung Jin Chang and Hubert P. H. Shum
Topics: Literature Review, Generative AI
Webpage Cite This Plain Text
Pattern Recognition (PR), 2026
Ziyi Chang, George Alex Koulieris, Hyung Jin Chang and Hubert P. H. Shum
Topics: Literature Review, Generative AI
Webpage Cite This Plain Text
Ziyi Chang, George Alex Koulieris, Hyung Jin Chang and Hubert P. H. Shum, "On the Design Fundamentals of Diffusion Models: A Survey," Pattern Recognition, pp. 111934, Elsevier, 2026.
Bibtex @article{chang25design,
author={Chang, Ziyi and Koulieris, George Alex and Chang, Hyung Jin and Shum, Hubert P. H.},
journal={Pattern Recognition},
title={On the Design Fundamentals of Diffusion Models: A Survey},
year={2026},
pages={111934},
doi={10.1016/j.patcog.2025.111934},
issn={0031-3203},
publisher={Elsevier},
}
RIS author={Chang, Ziyi and Koulieris, George Alex and Chang, Hyung Jin and Shum, Hubert P. H.},
journal={Pattern Recognition},
title={On the Design Fundamentals of Diffusion Models: A Survey},
year={2026},
pages={111934},
doi={10.1016/j.patcog.2025.111934},
issn={0031-3203},
publisher={Elsevier},
}
TY - JOUR
AU - Chang, Ziyi
AU - Koulieris, George Alex
AU - Chang, Hyung Jin
AU - Shum, Hubert P. H.
T2 - Pattern Recognition
TI - On the Design Fundamentals of Diffusion Models: A Survey
PY - 2026
SP - 111934
EP - 111934
DO - 10.1016/j.patcog.2025.111934
SN - 0031-3203
PB - Elsevier
ER -
PaperAU - Chang, Ziyi
AU - Koulieris, George Alex
AU - Chang, Hyung Jin
AU - Shum, Hubert P. H.
T2 - Pattern Recognition
TI - On the Design Fundamentals of Diffusion Models: A Survey
PY - 2026
SP - 111934
EP - 111934
DO - 10.1016/j.patcog.2025.111934
SN - 0031-3203
PB - Elsevier
ER -
Real-time and Controllable Reactive Motion Synthesis via Intention Guidance Impact Factor: 2.9†
Computer Graphics Forum (CGF), 2025
Xiaotang Zhang, Ziyi Chang, Qianhui Men and Hubert P. H. Shum
Topics: Character Animation, Interaction Modelling, Generative AI
Webpage Cite This Plain Text
Computer Graphics Forum (CGF), 2025
Xiaotang Zhang, Ziyi Chang, Qianhui Men and Hubert P. H. Shum
Topics: Character Animation, Interaction Modelling, Generative AI
Webpage Cite This Plain Text
Xiaotang Zhang, Ziyi Chang, Qianhui Men and Hubert P. H. Shum, "Real-time and Controllable Reactive Motion Synthesis via Intention Guidance," Computer Graphics Forum, vol. 44, no. 6, pp. e70222, Wiley, 2025.
Bibtex @article{zhang25realtime,
author={Zhang, Xiaotang and Chang, Ziyi and Men, Qianhui and Shum, Hubert P. H.},
journal={Computer Graphics Forum},
title={Real-time and Controllable Reactive Motion Synthesis via Intention Guidance},
year={2025},
volume={44},
number={6},
pages={e70222},
numpages={11},
doi={10.1111/cgf.70222},
issn={0167-7055},
publisher={Wiley},
}
RIS author={Zhang, Xiaotang and Chang, Ziyi and Men, Qianhui and Shum, Hubert P. H.},
journal={Computer Graphics Forum},
title={Real-time and Controllable Reactive Motion Synthesis via Intention Guidance},
year={2025},
volume={44},
number={6},
pages={e70222},
numpages={11},
doi={10.1111/cgf.70222},
issn={0167-7055},
publisher={Wiley},
}
TY - JOUR
AU - Zhang, Xiaotang
AU - Chang, Ziyi
AU - Men, Qianhui
AU - Shum, Hubert P. H.
T2 - Computer Graphics Forum
TI - Real-time and Controllable Reactive Motion Synthesis via Intention Guidance
PY - 2025
VL - 44
IS - 6
SP - e70222
EP - e70222
DO - 10.1111/cgf.70222
SN - 0167-7055
PB - Wiley
ER -
Paper GitHub YouTubeAU - Zhang, Xiaotang
AU - Chang, Ziyi
AU - Men, Qianhui
AU - Shum, Hubert P. H.
T2 - Computer Graphics Forum
TI - Real-time and Controllable Reactive Motion Synthesis via Intention Guidance
PY - 2025
VL - 44
IS - 6
SP - e70222
EP - e70222
DO - 10.1111/cgf.70222
SN - 0167-7055
PB - Wiley
ER -
HINT: High-quality INpainting Transformer with Mask-Aware Encoding and Enhanced Attention Impact Factor: 9.7† Top 10% Journal in Computer Science, Software Engineering† Citation: 58#
IEEE Transactions on Multimedia (TMM), 2024
Shuang Chen, Amir Atapour-Abarghouei and Hubert P. H. Shum
Topics: Generative AI
Webpage Cite This Plain Text
IEEE Transactions on Multimedia (TMM), 2024
Shuang Chen, Amir Atapour-Abarghouei and Hubert P. H. Shum
Topics: Generative AI
Webpage Cite This Plain Text
Shuang Chen, Amir Atapour-Abarghouei and Hubert P. H. Shum, "HINT: High-quality INpainting Transformer with Mask-Aware Encoding and Enhanced Attention," IEEE Transactions on Multimedia, vol. 26, pp. 7649-7660, IEEE, 2024.
Bibtex @article{chen24hint,
author={Chen, Shuang and Atapour-Abarghouei, Amir and Shum, Hubert P. H.},
journal={IEEE Transactions on Multimedia},
title={HINT: High-quality INpainting Transformer with Mask-Aware Encoding and Enhanced Attention},
year={2024},
volume={26},
pages={7649--7660},
numpages={12},
doi={10.1109/TMM.2024.3369897},
issn={1520-9210 },
publisher={IEEE},
}
RIS author={Chen, Shuang and Atapour-Abarghouei, Amir and Shum, Hubert P. H.},
journal={IEEE Transactions on Multimedia},
title={HINT: High-quality INpainting Transformer with Mask-Aware Encoding and Enhanced Attention},
year={2024},
volume={26},
pages={7649--7660},
numpages={12},
doi={10.1109/TMM.2024.3369897},
issn={1520-9210 },
publisher={IEEE},
}
TY - JOUR
AU - Chen, Shuang
AU - Atapour-Abarghouei, Amir
AU - Shum, Hubert P. H.
T2 - IEEE Transactions on Multimedia
TI - HINT: High-quality INpainting Transformer with Mask-Aware Encoding and Enhanced Attention
PY - 2024
VL - 26
SP - 7649
EP - 7660
DO - 10.1109/TMM.2024.3369897
SN - 1520-9210
PB - IEEE
ER -
Paper Supplementary Material GitHub YouTubeAU - Chen, Shuang
AU - Atapour-Abarghouei, Amir
AU - Shum, Hubert P. H.
T2 - IEEE Transactions on Multimedia
TI - HINT: High-quality INpainting Transformer with Mask-Aware Encoding and Enhanced Attention
PY - 2024
VL - 26
SP - 7649
EP - 7660
DO - 10.1109/TMM.2024.3369897
SN - 1520-9210
PB - IEEE
ER -
INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network Impact Factor: 1.2†
Software Impacts (SIMPAC), 2023
Shuang Chen, Amir Atapour-Abarghouei, Edmond S. L. Ho and Hubert P. H. Shum
Topics: Biomedical Engineering, Face Modelling, Medical Imaging, Responsible AI, Generative AI
Webpage Cite This Plain Text
Software Impacts (SIMPAC), 2023
Shuang Chen, Amir Atapour-Abarghouei, Edmond S. L. Ho and Hubert P. H. Shum
Topics: Biomedical Engineering, Face Modelling, Medical Imaging, Responsible AI, Generative AI
Webpage Cite This Plain Text
Shuang Chen, Amir Atapour-Abarghouei, Edmond S. L. Ho and Hubert P. H. Shum, "INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network," Software Impacts, vol. 17, pp. 100517, Elsevier, 2023.
Bibtex @article{chen23inclg,
author={Chen, Shuang and Atapour-Abarghouei, Amir and Ho, Edmond S. L. and Shum, Hubert P. H.},
journal={Software Impacts},
title={INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network},
year={2023},
volume={17},
pages={100517},
numpages={4},
doi={10.1016/j.simpa.2023.100517},
publisher={Elsevier},
}
RIS author={Chen, Shuang and Atapour-Abarghouei, Amir and Ho, Edmond S. L. and Shum, Hubert P. H.},
journal={Software Impacts},
title={INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network},
year={2023},
volume={17},
pages={100517},
numpages={4},
doi={10.1016/j.simpa.2023.100517},
publisher={Elsevier},
}
TY - JOUR
AU - Chen, Shuang
AU - Atapour-Abarghouei, Amir
AU - Ho, Edmond S. L.
AU - Shum, Hubert P. H.
T2 - Software Impacts
TI - INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network
PY - 2023
VL - 17
SP - 100517
EP - 100517
DO - 10.1016/j.simpa.2023.100517
PB - Elsevier
ER -
Paper CodeOcean GitHubAU - Chen, Shuang
AU - Atapour-Abarghouei, Amir
AU - Ho, Edmond S. L.
AU - Shum, Hubert P. H.
T2 - Software Impacts
TI - INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network
PY - 2023
VL - 17
SP - 100517
EP - 100517
DO - 10.1016/j.simpa.2023.100517
PB - Elsevier
ER -
3D Car Shape Reconstruction from a Contour Sketch using GAN and Lazy Learning Impact Factor: 2.9† Citation: 33#
Visual Computer (VC), 2022
Naoki Nozawa, Hubert P. H. Shum, Qi Feng, Edmond S. L. Ho and Shigeo Morishima
Topics: 3D Reconstruction, Surface Modelling, Artwork Analysis, Generative AI
Webpage Cite This Plain Text
Visual Computer (VC), 2022
Naoki Nozawa, Hubert P. H. Shum, Qi Feng, Edmond S. L. Ho and Shigeo Morishima
Topics: 3D Reconstruction, Surface Modelling, Artwork Analysis, Generative AI
Webpage Cite This Plain Text
Naoki Nozawa, Hubert P. H. Shum, Qi Feng, Edmond S. L. Ho and Shigeo Morishima, "3D Car Shape Reconstruction from a Contour Sketch using GAN and Lazy Learning," Visual Computer, vol. 38, no. 4, pp. 1317-1330, Springer, 2022.
Bibtex @article{nozawa21car,
author={Nozawa, Naoki and Shum, Hubert P. H. and Feng, Qi and Ho, Edmond S. L. and Morishima, Shigeo},
journal={Visual Computer},
title={3D Car Shape Reconstruction from a Contour Sketch using GAN and Lazy Learning},
year={2022},
volume={38},
number={4},
pages={1317--1330},
numpages={14},
doi={10.1007/s00371-020-02024-y},
issn={1432-2315},
publisher={Springer},
}
RIS author={Nozawa, Naoki and Shum, Hubert P. H. and Feng, Qi and Ho, Edmond S. L. and Morishima, Shigeo},
journal={Visual Computer},
title={3D Car Shape Reconstruction from a Contour Sketch using GAN and Lazy Learning},
year={2022},
volume={38},
number={4},
pages={1317--1330},
numpages={14},
doi={10.1007/s00371-020-02024-y},
issn={1432-2315},
publisher={Springer},
}
TY - JOUR
AU - Nozawa, Naoki
AU - Shum, Hubert P. H.
AU - Feng, Qi
AU - Ho, Edmond S. L.
AU - Morishima, Shigeo
T2 - Visual Computer
TI - 3D Car Shape Reconstruction from a Contour Sketch using GAN and Lazy Learning
PY - 2022
VL - 38
IS - 4
SP - 1317
EP - 1330
DO - 10.1007/s00371-020-02024-y
SN - 1432-2315
PB - Springer
ER -
Paper YouTubeAU - Nozawa, Naoki
AU - Shum, Hubert P. H.
AU - Feng, Qi
AU - Ho, Edmond S. L.
AU - Morishima, Shigeo
T2 - Visual Computer
TI - 3D Car Shape Reconstruction from a Contour Sketch using GAN and Lazy Learning
PY - 2022
VL - 38
IS - 4
SP - 1317
EP - 1330
DO - 10.1007/s00371-020-02024-y
SN - 1432-2315
PB - Springer
ER -
GAN-Based Reactive Motion Synthesis with Class-Aware Discriminators for Human-Human Interaction Impact Factor: 2.8† Citation: 46#
Computers and Graphics (C&G), 2022
Qianhui Men, Hubert P. H. Shum, Edmond S. L. Ho and Howard Leung
Topics: Character Animation, Interaction Modelling, Generative AI
Webpage Cite This Plain Text
Computers and Graphics (C&G), 2022
Qianhui Men, Hubert P. H. Shum, Edmond S. L. Ho and Howard Leung
Topics: Character Animation, Interaction Modelling, Generative AI
Webpage Cite This Plain Text
Qianhui Men, Hubert P. H. Shum, Edmond S. L. Ho and Howard Leung, "GAN-Based Reactive Motion Synthesis with Class-Aware Discriminators for Human-Human Interaction," Computers and Graphics, vol. 102, pp. 634-645, Elsevier, 2022.
Bibtex @article{men22gan,
author={Men, Qianhui and Shum, Hubert P. H. and Ho, Edmond S. L. and Leung, Howard},
journal={Computers and Graphics},
title={GAN-Based Reactive Motion Synthesis with Class-Aware Discriminators for Human-Human Interaction},
year={2022},
volume={102},
pages={634--645},
numpages={12},
doi={10.1016/j.cag.2021.09.014},
issn={0097-8493},
publisher={Elsevier},
}
RIS author={Men, Qianhui and Shum, Hubert P. H. and Ho, Edmond S. L. and Leung, Howard},
journal={Computers and Graphics},
title={GAN-Based Reactive Motion Synthesis with Class-Aware Discriminators for Human-Human Interaction},
year={2022},
volume={102},
pages={634--645},
numpages={12},
doi={10.1016/j.cag.2021.09.014},
issn={0097-8493},
publisher={Elsevier},
}
TY - JOUR
AU - Men, Qianhui
AU - Shum, Hubert P. H.
AU - Ho, Edmond S. L.
AU - Leung, Howard
T2 - Computers and Graphics
TI - GAN-Based Reactive Motion Synthesis with Class-Aware Discriminators for Human-Human Interaction
PY - 2022
VL - 102
SP - 634
EP - 645
DO - 10.1016/j.cag.2021.09.014
SN - 0097-8493
PB - Elsevier
ER -
Paper YouTubeAU - Men, Qianhui
AU - Shum, Hubert P. H.
AU - Ho, Edmond S. L.
AU - Leung, Howard
T2 - Computers and Graphics
TI - GAN-Based Reactive Motion Synthesis with Class-Aware Discriminators for Human-Human Interaction
PY - 2022
VL - 102
SP - 634
EP - 645
DO - 10.1016/j.cag.2021.09.014
SN - 0097-8493
PB - Elsevier
ER -
Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling REF 2021 Submitted Output Impact Factor: 6.5† Top 10% Journal in Computer Science, Software Engineering† Citation: 104#
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2021
He Wang, Edmond S. L. Ho, Hubert P. H. Shum and Zhanxing Zhu
Topics: Character Animation, Generative AI
Webpage Cite This Plain Text
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2021
He Wang, Edmond S. L. Ho, Hubert P. H. Shum and Zhanxing Zhu
Topics: Character Animation, Generative AI
Webpage Cite This Plain Text
He Wang, Edmond S. L. Ho, Hubert P. H. Shum and Zhanxing Zhu, "Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling," IEEE Transactions on Visualization and Computer Graphics, vol. 27, no. 1, pp. 216-227, IEEE, 2021.
Bibtex @article{wang21spatiotemporal,
author={Wang, He and Ho, Edmond S. L. and Shum, Hubert P. H. and Zhu, Zhanxing},
journal={IEEE Transactions on Visualization and Computer Graphics},
title={Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling},
year={2021},
volume={27},
number={1},
pages={216--227},
numpages={12},
doi={10.1109/TVCG.2019.2936810},
publisher={IEEE},
}
RIS author={Wang, He and Ho, Edmond S. L. and Shum, Hubert P. H. and Zhu, Zhanxing},
journal={IEEE Transactions on Visualization and Computer Graphics},
title={Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling},
year={2021},
volume={27},
number={1},
pages={216--227},
numpages={12},
doi={10.1109/TVCG.2019.2936810},
publisher={IEEE},
}
TY - JOUR
AU - Wang, He
AU - Ho, Edmond S. L.
AU - Shum, Hubert P. H.
AU - Zhu, Zhanxing
T2 - IEEE Transactions on Visualization and Computer Graphics
TI - Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling
PY - 2021
VL - 27
IS - 1
SP - 216
EP - 227
DO - 10.1109/TVCG.2019.2936810
PB - IEEE
ER -
Paper YouTube Part 1 YouTube Part 2AU - Wang, He
AU - Ho, Edmond S. L.
AU - Shum, Hubert P. H.
AU - Zhu, Zhanxing
T2 - IEEE Transactions on Visualization and Computer Graphics
TI - Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling
PY - 2021
VL - 27
IS - 1
SP - 216
EP - 227
DO - 10.1109/TVCG.2019.2936810
PB - IEEE
ER -
Conference Papers
Large-Scale Multi-Character Interaction Synthesis Core A* Conference‡
Proceedings of the 2025 ACM SIGGRAPH, 2025
Ziyi Chang, He Wang, George Alex Koulieris and Hubert P. H. Shum
Topics: Character Animation, Interaction Modelling, Crowd Modelling, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2025 ACM SIGGRAPH, 2025
Ziyi Chang, He Wang, George Alex Koulieris and Hubert P. H. Shum
Topics: Character Animation, Interaction Modelling, Crowd Modelling, Generative AI
Webpage Cite This Plain Text
Ziyi Chang, He Wang, George Alex Koulieris and Hubert P. H. Shum, "Large-Scale Multi-Character Interaction Synthesis," in Proceedings of the 2025 ACM SIGGRAPH, pp. Article 114, Vancouver, Canada, ACM, 2025.
Bibtex @inproceedings{chang25largescale,
author={Chang, Ziyi and Wang, He and Koulieris, George Alex and Shum, Hubert P. H.},
booktitle={Proceedings of the 2025 ACM SIGGRAPH},
title={Large-Scale Multi-Character Interaction Synthesis},
year={2025},
pages={Article 114},
numpages={10},
doi={10.1145/3721238.3730750},
isbn={9.80E+12},
publisher={ACM},
Address={New York, NY, USA},
location={Vancouver, Canada},
}
RIS author={Chang, Ziyi and Wang, He and Koulieris, George Alex and Shum, Hubert P. H.},
booktitle={Proceedings of the 2025 ACM SIGGRAPH},
title={Large-Scale Multi-Character Interaction Synthesis},
year={2025},
pages={Article 114},
numpages={10},
doi={10.1145/3721238.3730750},
isbn={9.80E+12},
publisher={ACM},
Address={New York, NY, USA},
location={Vancouver, Canada},
}
TY - CONF
AU - Chang, Ziyi
AU - Wang, He
AU - Koulieris, George Alex
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2025 ACM SIGGRAPH
TI - Large-Scale Multi-Character Interaction Synthesis
PY - 2025
SP - Article 114
EP - Article 114
DO - 10.1145/3721238.3730750
SN - 9.80E+12
PB - ACM
ER -
Paper Supplementary Material YouTubeAU - Chang, Ziyi
AU - Wang, He
AU - Koulieris, George Alex
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2025 ACM SIGGRAPH
TI - Large-Scale Multi-Character Interaction Synthesis
PY - 2025
SP - Article 114
EP - Article 114
DO - 10.1145/3721238.3730750
SN - 9.80E+12
PB - ACM
ER -
Motion In-Betweening for Densely Interacting Characters
Proceedings of the 2025 ACM SIGGRAPH Asia, 2025
Xiaotang Zhang, Ziyi Chang, Qianhui Men and Hubert P. H. Shum
Topics: Character Animation, Interaction Modelling, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2025 ACM SIGGRAPH Asia, 2025
Xiaotang Zhang, Ziyi Chang, Qianhui Men and Hubert P. H. Shum
Topics: Character Animation, Interaction Modelling, Generative AI
Webpage Cite This Plain Text
Xiaotang Zhang, Ziyi Chang, Qianhui Men and Hubert P. H. Shum, "Motion In-Betweening for Densely Interacting Characters," in Proceedings of the 2025 ACM SIGGRAPH Asia, pp. 96, Hong Kong, China, ACM, 2025.
Bibtex @inproceedings{zhang25otion,
author={Zhang, Xiaotang and Chang, Ziyi and Men, Qianhui and Shum, Hubert P. H.},
booktitle={Proceedings of the 2025 ACM SIGGRAPH Asia},
title={Motion In-Betweening for Densely Interacting Characters},
year={2025},
pages={96},
numpages={11},
doi={10.1145/3757377.3763950},
isbn={9.80E+12},
publisher={ACM},
Address={New York, NY, USA},
location={Hong Kong, China},
}
RIS author={Zhang, Xiaotang and Chang, Ziyi and Men, Qianhui and Shum, Hubert P. H.},
booktitle={Proceedings of the 2025 ACM SIGGRAPH Asia},
title={Motion In-Betweening for Densely Interacting Characters},
year={2025},
pages={96},
numpages={11},
doi={10.1145/3757377.3763950},
isbn={9.80E+12},
publisher={ACM},
Address={New York, NY, USA},
location={Hong Kong, China},
}
TY - CONF
AU - Zhang, Xiaotang
AU - Chang, Ziyi
AU - Men, Qianhui
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2025 ACM SIGGRAPH Asia
TI - Motion In-Betweening for Densely Interacting Characters
PY - 2025
SP - 96
EP - 96
DO - 10.1145/3757377.3763950
SN - 9.80E+12
PB - ACM
ER -
Paper YouTubeAU - Zhang, Xiaotang
AU - Chang, Ziyi
AU - Men, Qianhui
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2025 ACM SIGGRAPH Asia
TI - Motion In-Betweening for Densely Interacting Characters
PY - 2025
SP - 96
EP - 96
DO - 10.1145/3757377.3763950
SN - 9.80E+12
PB - ACM
ER -
SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM Oral Paper (Top 8.2% of 2458 Submissions) H5-Index: 131# Core A Conference‡
Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Shuang Chen, Haozheng Zhang, Amir Atapour-Abarghouei and Hubert P. H. Shum
Topics: Generative AI
Webpage Cite This Plain Text
Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Shuang Chen, Haozheng Zhang, Amir Atapour-Abarghouei and Hubert P. H. Shum
Topics: Generative AI
Webpage Cite This Plain Text
Shuang Chen, Haozheng Zhang, Amir Atapour-Abarghouei and Hubert P. H. Shum, "SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM," in WACV '25: Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 461-471, Arizona, USA, IEEE/CVF, 2025.
Bibtex @inproceedings{chen25sem,
author={Chen, Shuang and Zhang, Haozheng and Atapour-Abarghouei, Amir and Shum, Hubert P. H.},
booktitle={Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision},
series={WACV '25},
title={SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM},
year={2025},
pages={461--471},
doi={10.1109/WACV61041.2025.00055},
publisher={IEEE/CVF},
location={Arizona, USA},
}
RIS author={Chen, Shuang and Zhang, Haozheng and Atapour-Abarghouei, Amir and Shum, Hubert P. H.},
booktitle={Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision},
series={WACV '25},
title={SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM},
year={2025},
pages={461--471},
doi={10.1109/WACV61041.2025.00055},
publisher={IEEE/CVF},
location={Arizona, USA},
}
TY - CONF
AU - Chen, Shuang
AU - Zhang, Haozheng
AU - Atapour-Abarghouei, Amir
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision
TI - SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM
PY - 2025
SP - 461
EP - 471
DO - 10.1109/WACV61041.2025.00055
PB - IEEE/CVF
ER -
Paper YouTubeAU - Chen, Shuang
AU - Zhang, Haozheng
AU - Atapour-Abarghouei, Amir
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision
TI - SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM
PY - 2025
SP - 461
EP - 471
DO - 10.1109/WACV61041.2025.00055
PB - IEEE/CVF
ER -
MxT: Mamba x Transformer for Image Inpainting H5-Index: 57# Citation: 10#
Proceedings of the 2024 British Machine Vision Conference (BMVC), 2024
Shuang Chen, Amir Atapour-Abarghouei, Haozheng Zhang and Hubert P. H. Shum
Topics: Generative AI
Webpage Cite This Plain Text
Proceedings of the 2024 British Machine Vision Conference (BMVC), 2024
Shuang Chen, Amir Atapour-Abarghouei, Haozheng Zhang and Hubert P. H. Shum
Topics: Generative AI
Webpage Cite This Plain Text
Shuang Chen, Amir Atapour-Abarghouei, Haozheng Zhang and Hubert P. H. Shum, "MxT: Mamba x Transformer for Image Inpainting," in BMVC '24: Proceedings of the 2024 British Machine Vision Conference, Glasgow, UK, 2024.
Bibtex @inproceedings{chen24mxt,
author={Chen, Shuang and Atapour-Abarghouei, Amir and Zhang, Haozheng and Shum, Hubert P. H.},
booktitle={Proceedings of the 2024 British Machine Vision Conference},
series={BMVC '24},
title={MxT: Mamba x Transformer for Image Inpainting},
year={2024},
location={Glasgow, UK},
}
RIS author={Chen, Shuang and Atapour-Abarghouei, Amir and Zhang, Haozheng and Shum, Hubert P. H.},
booktitle={Proceedings of the 2024 British Machine Vision Conference},
series={BMVC '24},
title={MxT: Mamba x Transformer for Image Inpainting},
year={2024},
location={Glasgow, UK},
}
TY - CONF
AU - Chen, Shuang
AU - Atapour-Abarghouei, Amir
AU - Zhang, Haozheng
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2024 British Machine Vision Conference
TI - MxT: Mamba x Transformer for Image Inpainting
PY - 2024
ER -
Paper GitHub YouTubeAU - Chen, Shuang
AU - Atapour-Abarghouei, Amir
AU - Zhang, Haozheng
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2024 British Machine Vision Conference
TI - MxT: Mamba x Transformer for Image Inpainting
PY - 2024
ER -
Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling Best Paper Award H5-Index: 117#
Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024
Abril Corona-Figueroa, Hubert P. H. Shum and Chris G. Willcocks
Topics: 3D Reconstruction, Biomedical Engineering, Medical Imaging, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024
Abril Corona-Figueroa, Hubert P. H. Shum and Chris G. Willcocks
Topics: 3D Reconstruction, Biomedical Engineering, Medical Imaging, Generative AI
Webpage Cite This Plain Text
Abril Corona-Figueroa, Hubert P. H. Shum and Chris G. Willcocks, "Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling," in CVPRW '24: Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 2315-2324, Seattle, USA, IEEE/CVF, 2024.
Bibtex @inproceedings{coronafigueroaa24repeat,
author={Corona-Figueroa, Abril and Shum, Hubert P. H. and Willcocks, Chris G.},
booktitle={Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
series={CVPRW '24},
title={Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling},
year={2024},
pages={2315--2324},
numpages={10},
doi={10.1109/CVPRW63382.2024.00237},
publisher={IEEE/CVF},
location={Seattle, USA},
}
RIS author={Corona-Figueroa, Abril and Shum, Hubert P. H. and Willcocks, Chris G.},
booktitle={Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
series={CVPRW '24},
title={Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling},
year={2024},
pages={2315--2324},
numpages={10},
doi={10.1109/CVPRW63382.2024.00237},
publisher={IEEE/CVF},
location={Seattle, USA},
}
TY - CONF
AU - Corona-Figueroa, Abril
AU - Shum, Hubert P. H.
AU - Willcocks, Chris G.
T2 - Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
TI - Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling
PY - 2024
SP - 2315
EP - 2324
DO - 10.1109/CVPRW63382.2024.00237
PB - IEEE/CVF
ER -
PaperAU - Corona-Figueroa, Abril
AU - Shum, Hubert P. H.
AU - Willcocks, Chris G.
T2 - Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
TI - Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling
PY - 2024
SP - 2315
EP - 2324
DO - 10.1109/CVPRW63382.2024.00237
PB - IEEE/CVF
ER -
Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers H5-Index: 256# Core A* Conference‡ Citation: 10#
Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Abril Corona-Figueroa, Sam Bond-Taylor, Neelanjan Bhowmik, Yona Falinie A. Gaus, Toby P. Breckon, Hubert P. H. Shum and Chris G. Willcocks
Topics: 3D Reconstruction, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Abril Corona-Figueroa, Sam Bond-Taylor, Neelanjan Bhowmik, Yona Falinie A. Gaus, Toby P. Breckon, Hubert P. H. Shum and Chris G. Willcocks
Topics: 3D Reconstruction, Generative AI
Webpage Cite This Plain Text
Abril Corona-Figueroa, Sam Bond-Taylor, Neelanjan Bhowmik, Yona Falinie A. Gaus, Toby P. Breckon, Hubert P. H. Shum and Chris G. Willcocks, "Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers," in ICCV '23: Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision, pp. 14539-14548, Paris, France, IEEE/CVF, Oct 2023.
Bibtex @inproceedings{coronafigueroaa23unaligned,
author={Corona-Figueroa, Abril and Bond-Taylor, Sam and Bhowmik, Neelanjan and Gaus, Yona Falinie A. and Breckon, Toby P. and Shum, Hubert P. H. and Willcocks, Chris G.},
booktitle={Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision},
series={ICCV '23},
title={Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers},
year={2023},
month={10},
pages={14539--14548},
numpages={10},
doi={10.1109/ICCV51070.2023.01341},
publisher={IEEE/CVF},
location={Paris, France},
}
RIS author={Corona-Figueroa, Abril and Bond-Taylor, Sam and Bhowmik, Neelanjan and Gaus, Yona Falinie A. and Breckon, Toby P. and Shum, Hubert P. H. and Willcocks, Chris G.},
booktitle={Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision},
series={ICCV '23},
title={Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers},
year={2023},
month={10},
pages={14539--14548},
numpages={10},
doi={10.1109/ICCV51070.2023.01341},
publisher={IEEE/CVF},
location={Paris, France},
}
TY - CONF
AU - Corona-Figueroa, Abril
AU - Bond-Taylor, Sam
AU - Bhowmik, Neelanjan
AU - Gaus, Yona Falinie A.
AU - Breckon, Toby P.
AU - Shum, Hubert P. H.
AU - Willcocks, Chris G.
T2 - Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision
TI - Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers
PY - 2023
Y1 - 10 2023
SP - 14539
EP - 14548
DO - 10.1109/ICCV51070.2023.01341
PB - IEEE/CVF
ER -
Paper Supplementary Material YouTubeAU - Corona-Figueroa, Abril
AU - Bond-Taylor, Sam
AU - Bhowmik, Neelanjan
AU - Gaus, Yona Falinie A.
AU - Breckon, Toby P.
AU - Shum, Hubert P. H.
AU - Willcocks, Chris G.
T2 - Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision
TI - Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers
PY - 2023
Y1 - 10 2023
SP - 14539
EP - 14548
DO - 10.1109/ICCV51070.2023.01341
PB - IEEE/CVF
ER -
Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptation Core A* Conference‡
Proceedings of the 2023 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2023
Qi Feng, Hubert P. H. Shum and Shigeo Morishima
Topics: Virtual Reality, Environment Sensing, Video Analysis, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2023 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2023
Qi Feng, Hubert P. H. Shum and Shigeo Morishima
Topics: Virtual Reality, Environment Sensing, Video Analysis, Generative AI
Webpage Cite This Plain Text
Qi Feng, Hubert P. H. Shum and Shigeo Morishima, "Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptation," in ISMAR '23: Proceedings of the 2023 IEEE International Symposium on Mixed and Augmented Reality, pp. 405-414, Sydney, Australia, IEEE, Oct 2023.
Bibtex @inproceedings{feng23enhancing,
author={Feng, Qi and Shum, Hubert P. H. and Morishima, Shigeo},
booktitle={Proceedings of the 2023 IEEE International Symposium on Mixed and Augmented Reality},
series={ISMAR '23},
title={Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptation},
year={2023},
month={10},
pages={405-414},
numpages={10},
doi={10.1109/ISMAR59233.2023.00055},
publisher={IEEE},
location={Sydney, Australia},
}
RIS author={Feng, Qi and Shum, Hubert P. H. and Morishima, Shigeo},
booktitle={Proceedings of the 2023 IEEE International Symposium on Mixed and Augmented Reality},
series={ISMAR '23},
title={Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptation},
year={2023},
month={10},
pages={405-414},
numpages={10},
doi={10.1109/ISMAR59233.2023.00055},
publisher={IEEE},
location={Sydney, Australia},
}
TY - CONF
AU - Feng, Qi
AU - Shum, Hubert P. H.
AU - Morishima, Shigeo
T2 - Proceedings of the 2023 IEEE International Symposium on Mixed and Augmented Reality
TI - Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptation
PY - 2023
Y1 - 10 2023
SP - 405-414
EP - 405-414
DO - 10.1109/ISMAR59233.2023.00055
PB - IEEE
ER -
Paper YouTubeAU - Feng, Qi
AU - Shum, Hubert P. H.
AU - Morishima, Shigeo
T2 - Proceedings of the 2023 IEEE International Symposium on Mixed and Augmented Reality
TI - Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptation
PY - 2023
Y1 - 10 2023
SP - 405-414
EP - 405-414
DO - 10.1109/ISMAR59233.2023.00055
PB - IEEE
ER -
Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models Citation: 26#
Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications (GRAPP), 2023
Ziyi Chang, Edmund J. C. Findlay, Haozheng Zhang and Hubert P. H. Shum
Topics: Character Animation, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications (GRAPP), 2023
Ziyi Chang, Edmund J. C. Findlay, Haozheng Zhang and Hubert P. H. Shum
Topics: Character Animation, Generative AI
Webpage Cite This Plain Text
Ziyi Chang, Edmund J. C. Findlay, Haozheng Zhang and Hubert P. H. Shum, "Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models," in GRAPP '23: Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications, pp. 64-74, Lisbon, Portugal, SciTePress, Feb 2023.
Bibtex @inproceedings{chang23unifying,
author={Chang, Ziyi and Findlay, Edmund J. C. and Zhang, Haozheng and Shum, Hubert P. H.},
booktitle={Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications},
series={GRAPP '23},
title={Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models},
year={2023},
month={2},
pages={64--74},
numpages={11},
doi={10.5220/0011631000003417},
issn={2184-4321},
isbn={978-989-758-634-7},
publisher={SciTePress},
location={Lisbon, Portugal},
}
RIS author={Chang, Ziyi and Findlay, Edmund J. C. and Zhang, Haozheng and Shum, Hubert P. H.},
booktitle={Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications},
series={GRAPP '23},
title={Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models},
year={2023},
month={2},
pages={64--74},
numpages={11},
doi={10.5220/0011631000003417},
issn={2184-4321},
isbn={978-989-758-634-7},
publisher={SciTePress},
location={Lisbon, Portugal},
}
TY - CONF
AU - Chang, Ziyi
AU - Findlay, Edmund J. C.
AU - Zhang, Haozheng
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications
TI - Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
PY - 2023
Y1 - 2 2023
SP - 64
EP - 74
DO - 10.5220/0011631000003417
SN - 2184-4321
PB - SciTePress
ER -
Paper YouTubeAU - Chang, Ziyi
AU - Findlay, Edmund J. C.
AU - Zhang, Haozheng
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications
TI - Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
PY - 2023
Y1 - 2 2023
SP - 64
EP - 74
DO - 10.5220/0011631000003417
SN - 2184-4321
PB - SciTePress
ER -
3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models Core A Conference‡
Proceedings of the 2022 ACM Symposium on Virtual Reality Software and Technology (VRST), 2022
Ziyi Chang, George Alex Koulieris and Hubert P. H. Shum
Topics: 3D Reconstruction, Surface Modelling, Artwork Analysis, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2022 ACM Symposium on Virtual Reality Software and Technology (VRST), 2022
Ziyi Chang, George Alex Koulieris and Hubert P. H. Shum
Topics: 3D Reconstruction, Surface Modelling, Artwork Analysis, Generative AI
Webpage Cite This Plain Text
Ziyi Chang, George Alex Koulieris and Hubert P. H. Shum, "3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models," in VRST '22: Proceedings of the 2022 ACM Symposium on Virtual Reality Software and Technology, pp. 1-10, Tsukuba, Japan, ACM, Nov 2022.
Bibtex @inproceedings{chang22reconstruction,
author={Chang, Ziyi and Koulieris, George Alex and Shum, Hubert P. H.},
booktitle={Proceedings of the 2022 ACM Symposium on Virtual Reality Software and Technology},
series={VRST '22},
title={3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models},
year={2022},
month={11},
pages={1--10},
numpages={10},
doi={10.1145/3562939.3565632},
isbn={9.78E+12},
publisher={ACM},
Address={New York, NY, USA},
location={Tsukuba, Japan},
}
RIS author={Chang, Ziyi and Koulieris, George Alex and Shum, Hubert P. H.},
booktitle={Proceedings of the 2022 ACM Symposium on Virtual Reality Software and Technology},
series={VRST '22},
title={3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models},
year={2022},
month={11},
pages={1--10},
numpages={10},
doi={10.1145/3562939.3565632},
isbn={9.78E+12},
publisher={ACM},
Address={New York, NY, USA},
location={Tsukuba, Japan},
}
TY - CONF
AU - Chang, Ziyi
AU - Koulieris, George Alex
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2022 ACM Symposium on Virtual Reality Software and Technology
TI - 3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models
PY - 2022
Y1 - 11 2022
SP - 1
EP - 10
DO - 10.1145/3562939.3565632
SN - 9.78E+12
PB - ACM
ER -
Paper GitHub YouTubeAU - Chang, Ziyi
AU - Koulieris, George Alex
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2022 ACM Symposium on Virtual Reality Software and Technology
TI - 3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models
PY - 2022
Y1 - 11 2022
SP - 1
EP - 10
DO - 10.1145/3562939.3565632
SN - 9.78E+12
PB - ACM
ER -
MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-Aware CT-projections from a Single X-ray Citation: 151#
Proceedings of the 2022 International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2022
Abril Corona-Figueroa, Jonathan Frawley, Sam Bond-Taylor, Sarath Bethapudi, Hubert P. H. Shum and Chris G. Willcocks
Topics: Biomedical Engineering, 3D Reconstruction, Medical Imaging, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2022 International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2022
Abril Corona-Figueroa, Jonathan Frawley, Sam Bond-Taylor, Sarath Bethapudi, Hubert P. H. Shum and Chris G. Willcocks
Topics: Biomedical Engineering, 3D Reconstruction, Medical Imaging, Generative AI
Webpage Cite This Plain Text
Abril Corona-Figueroa, Jonathan Frawley, Sam Bond-Taylor, Sarath Bethapudi, Hubert P. H. Shum and Chris G. Willcocks, "MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-Aware CT-projections from a Single X-ray," in EMBC '22: Proceedings of the 2022 International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 3843-3848, Glasgow, UK, IEEE, Jul 2022.
Bibtex @inproceedings{coronafigueroaa22mednerf,
author={Corona-Figueroa, Abril and Frawley, Jonathan and Bond-Taylor, Sam and Bethapudi, Sarath and Shum, Hubert P. H. and Willcocks, Chris G.},
booktitle={Proceedings of the 2022 International Conference of the IEEE Engineering in Medicine and Biology Society},
series={EMBC '22},
title={MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-Aware CT-projections from a Single X-ray},
year={2022},
month={7},
pages={3843--3848},
numpages={6},
doi={10.1109/EMBC48229.2022.9871757},
publisher={IEEE},
location={Glasgow, UK},
}
RIS author={Corona-Figueroa, Abril and Frawley, Jonathan and Bond-Taylor, Sam and Bethapudi, Sarath and Shum, Hubert P. H. and Willcocks, Chris G.},
booktitle={Proceedings of the 2022 International Conference of the IEEE Engineering in Medicine and Biology Society},
series={EMBC '22},
title={MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-Aware CT-projections from a Single X-ray},
year={2022},
month={7},
pages={3843--3848},
numpages={6},
doi={10.1109/EMBC48229.2022.9871757},
publisher={IEEE},
location={Glasgow, UK},
}
TY - CONF
AU - Corona-Figueroa, Abril
AU - Frawley, Jonathan
AU - Bond-Taylor, Sam
AU - Bethapudi, Sarath
AU - Shum, Hubert P. H.
AU - Willcocks, Chris G.
T2 - Proceedings of the 2022 International Conference of the IEEE Engineering in Medicine and Biology Society
TI - MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-Aware CT-projections from a Single X-ray
PY - 2022
Y1 - 7 2022
SP - 3843
EP - 3848
DO - 10.1109/EMBC48229.2022.9871757
PB - IEEE
ER -
Paper GitHubAU - Corona-Figueroa, Abril
AU - Frawley, Jonathan
AU - Bond-Taylor, Sam
AU - Bethapudi, Sarath
AU - Shum, Hubert P. H.
AU - Willcocks, Chris G.
T2 - Proceedings of the 2022 International Conference of the IEEE Engineering in Medicine and Biology Society
TI - MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-Aware CT-projections from a Single X-ray
PY - 2022
Y1 - 7 2022
SP - 3843
EP - 3848
DO - 10.1109/EMBC48229.2022.9871757
PB - IEEE
ER -
A Feasibility Study on Image Inpainting for Non-Cleft Lip Generation from Patients with Cleft Lip Oral Paper
Proceedings of the 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2022
Shuang Chen, Amir Atapour-Abarghouei, Jane Kerby, Edmond S. L. Ho, David C. G. Sainsbury, Sophie Butterworth and Hubert P. H. Shum
Topics: Biomedical Engineering, Face Modelling, Medical Imaging, Responsible AI, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2022
Shuang Chen, Amir Atapour-Abarghouei, Jane Kerby, Edmond S. L. Ho, David C. G. Sainsbury, Sophie Butterworth and Hubert P. H. Shum
Topics: Biomedical Engineering, Face Modelling, Medical Imaging, Responsible AI, Generative AI
Webpage Cite This Plain Text
Shuang Chen, Amir Atapour-Abarghouei, Jane Kerby, Edmond S. L. Ho, David C. G. Sainsbury, Sophie Butterworth and Hubert P. H. Shum, "A Feasibility Study on Image Inpainting for Non-Cleft Lip Generation from Patients with Cleft Lip," in BHI '22: Proceedings of the 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics, pp. 1-4, Ioannina, Greece, IEEE, Sep 2022.
Bibtex @inproceedings{chen22feasibility,
author={Chen, Shuang and Atapour-Abarghouei, Amir and Kerby, Jane and Ho, Edmond S. L. and Sainsbury, David C. G. and Butterworth, Sophie and Shum, Hubert P. H.},
booktitle={Proceedings of the 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics},
series={BHI '22},
title={A Feasibility Study on Image Inpainting for Non-Cleft Lip Generation from Patients with Cleft Lip},
year={2022},
month={9},
pages={1--4},
numpages={4},
doi={10.1109/BHI56158.2022.9926917},
publisher={IEEE},
location={Ioannina, Greece},
}
RIS author={Chen, Shuang and Atapour-Abarghouei, Amir and Kerby, Jane and Ho, Edmond S. L. and Sainsbury, David C. G. and Butterworth, Sophie and Shum, Hubert P. H.},
booktitle={Proceedings of the 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics},
series={BHI '22},
title={A Feasibility Study on Image Inpainting for Non-Cleft Lip Generation from Patients with Cleft Lip},
year={2022},
month={9},
pages={1--4},
numpages={4},
doi={10.1109/BHI56158.2022.9926917},
publisher={IEEE},
location={Ioannina, Greece},
}
TY - CONF
AU - Chen, Shuang
AU - Atapour-Abarghouei, Amir
AU - Kerby, Jane
AU - Ho, Edmond S. L.
AU - Sainsbury, David C. G.
AU - Butterworth, Sophie
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics
TI - A Feasibility Study on Image Inpainting for Non-Cleft Lip Generation from Patients with Cleft Lip
PY - 2022
Y1 - 9 2022
SP - 1
EP - 4
DO - 10.1109/BHI56158.2022.9926917
PB - IEEE
ER -
Paper GitHubAU - Chen, Shuang
AU - Atapour-Abarghouei, Amir
AU - Kerby, Jane
AU - Ho, Edmond S. L.
AU - Sainsbury, David C. G.
AU - Butterworth, Sophie
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics
TI - A Feasibility Study on Image Inpainting for Non-Cleft Lip Generation from Patients with Cleft Lip
PY - 2022
Y1 - 9 2022
SP - 1
EP - 4
DO - 10.1109/BHI56158.2022.9926917
PB - IEEE
ER -
Makeup Style Transfer on Low-Quality Images with Weighted Multi-Scale Attention H5-Index: 68# Citation: 14#
Proceedings of the 2020 International Conference on Pattern Recognition (ICPR), 2020
Daniel Organisciak, Edmond S. L. Ho and Hubert P. H. Shum
Topics: Face Modelling, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2020 International Conference on Pattern Recognition (ICPR), 2020
Daniel Organisciak, Edmond S. L. Ho and Hubert P. H. Shum
Topics: Face Modelling, Generative AI
Webpage Cite This Plain Text
Daniel Organisciak, Edmond S. L. Ho and Hubert P. H. Shum, "Makeup Style Transfer on Low-Quality Images with Weighted Multi-Scale Attention," in ICPR '20: Proceedings of the 2020 International Conference on Pattern Recognition, pp. 6011-6018, Milan, Italy, Jan 2020.
Bibtex @inproceedings{organisciak20makeup,
author={Organisciak, Daniel and Ho, Edmond S. L. and Shum, Hubert P. H.},
booktitle={Proceedings of the 2020 International Conference on Pattern Recognition},
series={ICPR '20},
title={Makeup Style Transfer on Low-Quality Images with Weighted Multi-Scale Attention},
year={2020},
month={1},
pages={6011--6018},
numpages={8},
doi={10.1109/ICPR48806.2021.9412604},
location={Milan, Italy},
}
RIS author={Organisciak, Daniel and Ho, Edmond S. L. and Shum, Hubert P. H.},
booktitle={Proceedings of the 2020 International Conference on Pattern Recognition},
series={ICPR '20},
title={Makeup Style Transfer on Low-Quality Images with Weighted Multi-Scale Attention},
year={2020},
month={1},
pages={6011--6018},
numpages={8},
doi={10.1109/ICPR48806.2021.9412604},
location={Milan, Italy},
}
TY - CONF
AU - Organisciak, Daniel
AU - Ho, Edmond S. L.
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2020 International Conference on Pattern Recognition
TI - Makeup Style Transfer on Low-Quality Images with Weighted Multi-Scale Attention
PY - 2020
Y1 - 1 2020
SP - 6011
EP - 6018
DO - 10.1109/ICPR48806.2021.9412604
ER -
Paper Supplementary Material YouTubeAU - Organisciak, Daniel
AU - Ho, Edmond S. L.
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2020 International Conference on Pattern Recognition
TI - Makeup Style Transfer on Low-Quality Images with Weighted Multi-Scale Attention
PY - 2020
Y1 - 1 2020
SP - 6011
EP - 6018
DO - 10.1109/ICPR48806.2021.9412604
ER -
Single Sketch Image Based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning Best Student Paper Award Citation: 15#
Proceedings of the 2020 International Conference on Computer Graphics Theory and Applications (GRAPP), 2020
Naoki Nozawa, Hubert P. H. Shum, Edmond S. L. Ho and Shigeo Morishima
Topics: 3D Reconstruction, Surface Modelling, Artwork Analysis, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2020 International Conference on Computer Graphics Theory and Applications (GRAPP), 2020
Naoki Nozawa, Hubert P. H. Shum, Edmond S. L. Ho and Shigeo Morishima
Topics: 3D Reconstruction, Surface Modelling, Artwork Analysis, Generative AI
Webpage Cite This Plain Text
Naoki Nozawa, Hubert P. H. Shum, Edmond S. L. Ho and Shigeo Morishima, "Single Sketch Image Based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning," in GRAPP '20: Proceedings of the 2020 International Conference on Computer Graphics Theory and Applications, pp. 179-190, Valletta, Malta, SciTePress, Feb 2020.
Bibtex @inproceedings{nozawa20single,
author={Nozawa, Naoki and Shum, Hubert P. H. and Ho, Edmond S. L. and Morishima, Shigeo},
booktitle={Proceedings of the 2020 International Conference on Computer Graphics Theory and Applications},
series={GRAPP '20},
title={Single Sketch Image Based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning},
year={2020},
month={2},
pages={179--190},
numpages={12},
doi={10.5220/0009157001790190},
issn={2184-4321},
isbn={978-989-758-402-2},
publisher={SciTePress},
location={Valletta, Malta},
}
RIS author={Nozawa, Naoki and Shum, Hubert P. H. and Ho, Edmond S. L. and Morishima, Shigeo},
booktitle={Proceedings of the 2020 International Conference on Computer Graphics Theory and Applications},
series={GRAPP '20},
title={Single Sketch Image Based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning},
year={2020},
month={2},
pages={179--190},
numpages={12},
doi={10.5220/0009157001790190},
issn={2184-4321},
isbn={978-989-758-402-2},
publisher={SciTePress},
location={Valletta, Malta},
}
TY - CONF
AU - Nozawa, Naoki
AU - Shum, Hubert P. H.
AU - Ho, Edmond S. L.
AU - Morishima, Shigeo
T2 - Proceedings of the 2020 International Conference on Computer Graphics Theory and Applications
TI - Single Sketch Image Based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning
PY - 2020
Y1 - 2 2020
SP - 179
EP - 190
DO - 10.5220/0009157001790190
SN - 2184-4321
PB - SciTePress
ER -
Paper YouTubeAU - Nozawa, Naoki
AU - Shum, Hubert P. H.
AU - Ho, Edmond S. L.
AU - Morishima, Shigeo
T2 - Proceedings of the 2020 International Conference on Computer Graphics Theory and Applications
TI - Single Sketch Image Based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning
PY - 2020
Y1 - 2 2020
SP - 179
EP - 190
DO - 10.5220/0009157001790190
SN - 2184-4321
PB - SciTePress
ER -
DSPP: Deep Shape and Pose Priors of Humans
Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG), 2019
Shanfeng Hu, Hubert P. H. Shum and Antonio Mucherino
Topics: Surface Modelling, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG), 2019
Shanfeng Hu, Hubert P. H. Shum and Antonio Mucherino
Topics: Surface Modelling, Generative AI
Webpage Cite This Plain Text
Shanfeng Hu, Hubert P. H. Shum and Antonio Mucherino, "DSPP: Deep Shape and Pose Priors of Humans," in MIG '19: Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games, pp. 1:1-1:6, Newcastle upon Tyne, UK, ACM, Oct 2019.
Bibtex @inproceedings{hu19dspp,
author={Hu, Shanfeng and Shum, Hubert P. H. and Mucherino, Antonio},
booktitle={Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games},
series={MIG '19},
title={DSPP: Deep Shape and Pose Priors of Humans},
year={2019},
month={10},
pages={1:1--1:6},
numpages={6},
doi={10.1145/3359566.3360051},
isbn={978-1-4503-6994-7},
publisher={ACM},
Address={New York, NY, USA},
location={Newcastle upon Tyne, UK},
}
RIS author={Hu, Shanfeng and Shum, Hubert P. H. and Mucherino, Antonio},
booktitle={Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games},
series={MIG '19},
title={DSPP: Deep Shape and Pose Priors of Humans},
year={2019},
month={10},
pages={1:1--1:6},
numpages={6},
doi={10.1145/3359566.3360051},
isbn={978-1-4503-6994-7},
publisher={ACM},
Address={New York, NY, USA},
location={Newcastle upon Tyne, UK},
}
TY - CONF
AU - Hu, Shanfeng
AU - Shum, Hubert P. H.
AU - Mucherino, Antonio
T2 - Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games
TI - DSPP: Deep Shape and Pose Priors of Humans
PY - 2019
Y1 - 10 2019
SP - 1:1
EP - 1:6
DO - 10.1145/3359566.3360051
SN - 978-1-4503-6994-7
PB - ACM
ER -
Paper YouTubeAU - Hu, Shanfeng
AU - Shum, Hubert P. H.
AU - Mucherino, Antonio
T2 - Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games
TI - DSPP: Deep Shape and Pose Priors of Humans
PY - 2019
Y1 - 10 2019
SP - 1:1
EP - 1:6
DO - 10.1145/3359566.3360051
SN - 978-1-4503-6994-7
PB - ACM
ER -
Posters
Denoising Diffusion Probabilistic Models for Styled Walking Synthesis
Proceedings of the 2022 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) Posters, 2022
Edmund J. C. Findlay, Haozheng Zhang, Ziyi Chang and Hubert P. H. Shum
Topics: Character Animation, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2022 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) Posters, 2022
Edmund J. C. Findlay, Haozheng Zhang, Ziyi Chang and Hubert P. H. Shum
Topics: Character Animation, Generative AI
Webpage Cite This Plain Text
Edmund J. C. Findlay, Haozheng Zhang, Ziyi Chang and Hubert P. H. Shum, "Denoising Diffusion Probabilistic Models for Styled Walking Synthesis," in MIG '22: Proceedings of the 2022 ACM SIGGRAPH Conference on Motion, Interaction and Games, Guanajuato, Mexico, ACM, 2022.
Bibtex @inproceedings{edmund22style,
author={Findlay, Edmund J. C. and Zhang, Haozheng and Chang, Ziyi and Shum, Hubert P. H.},
booktitle={Proceedings of the 2022 ACM SIGGRAPH Conference on Motion, Interaction and Games},
series={MIG '22},
title={Denoising Diffusion Probabilistic Models for Styled Walking Synthesis},
year={2022},
publisher={ACM},
Address={New York, NY, USA},
location={Guanajuato, Mexico},
}
RIS author={Findlay, Edmund J. C. and Zhang, Haozheng and Chang, Ziyi and Shum, Hubert P. H.},
booktitle={Proceedings of the 2022 ACM SIGGRAPH Conference on Motion, Interaction and Games},
series={MIG '22},
title={Denoising Diffusion Probabilistic Models for Styled Walking Synthesis},
year={2022},
publisher={ACM},
Address={New York, NY, USA},
location={Guanajuato, Mexico},
}
TY - CONF
AU - Findlay, Edmund J. C.
AU - Zhang, Haozheng
AU - Chang, Ziyi
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2022 ACM SIGGRAPH Conference on Motion, Interaction and Games
TI - Denoising Diffusion Probabilistic Models for Styled Walking Synthesis
PY - 2022
PB - ACM
ER -
Paper YouTubeAU - Findlay, Edmund J. C.
AU - Zhang, Haozheng
AU - Chang, Ziyi
AU - Shum, Hubert P. H.
T2 - Proceedings of the 2022 ACM SIGGRAPH Conference on Motion, Interaction and Games
TI - Denoising Diffusion Probabilistic Models for Styled Walking Synthesis
PY - 2022
PB - ACM
ER -
3D Car Shape Reconstruction from a Single Sketch Image Best Poster Award
Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) Posters, 2019
Naoki Nozawa, Hubert P. H. Shum, Edmond S. L. Ho and Shigeo Morishima
Topics: 3D Reconstruction, Surface Modelling, Artwork Analysis, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) Posters, 2019
Naoki Nozawa, Hubert P. H. Shum, Edmond S. L. Ho and Shigeo Morishima
Topics: 3D Reconstruction, Surface Modelling, Artwork Analysis, Generative AI
Webpage Cite This Plain Text
Naoki Nozawa, Hubert P. H. Shum, Edmond S. L. Ho and Shigeo Morishima, "3D Car Shape Reconstruction from a Single Sketch Image," in MIG '19: Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games, pp. 37:1-37:2, Newcastle upon Tyne, UK, ACM, Oct 2019.
Bibtex @inproceedings{nozawa193dcar,
author={Nozawa, Naoki and Shum, Hubert P. H. and Ho, Edmond S. L. and Morishima, Shigeo},
booktitle={Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games},
series={MIG '19},
title={3D Car Shape Reconstruction from a Single Sketch Image},
year={2019},
month={10},
pages={37:1--37:2},
numpages={2},
doi={10.1145/3359566.3364693},
isbn={978-1-4503-6994-7},
publisher={ACM},
Address={New York, NY, USA},
location={Newcastle upon Tyne, UK},
}
RIS author={Nozawa, Naoki and Shum, Hubert P. H. and Ho, Edmond S. L. and Morishima, Shigeo},
booktitle={Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games},
series={MIG '19},
title={3D Car Shape Reconstruction from a Single Sketch Image},
year={2019},
month={10},
pages={37:1--37:2},
numpages={2},
doi={10.1145/3359566.3364693},
isbn={978-1-4503-6994-7},
publisher={ACM},
Address={New York, NY, USA},
location={Newcastle upon Tyne, UK},
}
TY - CONF
AU - Nozawa, Naoki
AU - Shum, Hubert P. H.
AU - Ho, Edmond S. L.
AU - Morishima, Shigeo
T2 - Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games
TI - 3D Car Shape Reconstruction from a Single Sketch Image
PY - 2019
Y1 - 10 2019
SP - 37:1
EP - 37:2
DO - 10.1145/3359566.3364693
SN - 978-1-4503-6994-7
PB - ACM
ER -
PaperAU - Nozawa, Naoki
AU - Shum, Hubert P. H.
AU - Ho, Edmond S. L.
AU - Morishima, Shigeo
T2 - Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games
TI - 3D Car Shape Reconstruction from a Single Sketch Image
PY - 2019
Y1 - 10 2019
SP - 37:1
EP - 37:2
DO - 10.1145/3359566.3364693
SN - 978-1-4503-6994-7
PB - ACM
ER -
Prior-Less 3D Human Shape Reconstruction with an Earth Mover's Distance Informed CNN
Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) Posters, 2019
Jingtian Zhang, Hubert P. H. Shum, Kevin D. McCay and Edmond S. L. Ho
Topics: 3D Reconstruction, Surface Modelling, Generative AI
Webpage Cite This Plain Text
Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) Posters, 2019
Jingtian Zhang, Hubert P. H. Shum, Kevin D. McCay and Edmond S. L. Ho
Topics: 3D Reconstruction, Surface Modelling, Generative AI
Webpage Cite This Plain Text
Jingtian Zhang, Hubert P. H. Shum, Kevin D. McCay and Edmond S. L. Ho, "Prior-Less 3D Human Shape Reconstruction with an Earth Mover's Distance Informed CNN," in MIG '19: Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games, pp. 44:1-44:2, Newcastle upon Tyne, UK, ACM, Oct 2019.
Bibtex @inproceedings{zhang19priorless,
author={Zhang, Jingtian and Shum, Hubert P. H. and McCay, Kevin D. and Ho, Edmond S. L.},
booktitle={Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games},
series={MIG '19},
title={Prior-Less 3D Human Shape Reconstruction with an Earth Mover's Distance Informed CNN},
year={2019},
month={10},
pages={44:1--44:2},
numpages={2},
doi={10.1145/3359566.3364694},
isbn={978-1-4503-6994-7},
publisher={ACM},
Address={New York, NY, USA},
location={Newcastle upon Tyne, UK},
}
RIS author={Zhang, Jingtian and Shum, Hubert P. H. and McCay, Kevin D. and Ho, Edmond S. L.},
booktitle={Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games},
series={MIG '19},
title={Prior-Less 3D Human Shape Reconstruction with an Earth Mover's Distance Informed CNN},
year={2019},
month={10},
pages={44:1--44:2},
numpages={2},
doi={10.1145/3359566.3364694},
isbn={978-1-4503-6994-7},
publisher={ACM},
Address={New York, NY, USA},
location={Newcastle upon Tyne, UK},
}
TY - CONF
AU - Zhang, Jingtian
AU - Shum, Hubert P. H.
AU - McCay, Kevin D.
AU - Ho, Edmond S. L.
T2 - Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games
TI - Prior-Less 3D Human Shape Reconstruction with an Earth Mover's Distance Informed CNN
PY - 2019
Y1 - 10 2019
SP - 44:1
EP - 44:2
DO - 10.1145/3359566.3364694
SN - 978-1-4503-6994-7
PB - ACM
ER -
PaperAU - Zhang, Jingtian
AU - Shum, Hubert P. H.
AU - McCay, Kevin D.
AU - Ho, Edmond S. L.
T2 - Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games
TI - Prior-Less 3D Human Shape Reconstruction with an Earth Mover's Distance Informed CNN
PY - 2019
Y1 - 10 2019
SP - 44:1
EP - 44:2
DO - 10.1145/3359566.3364694
SN - 978-1-4503-6994-7
PB - ACM
ER -
Eprints
TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba
arXiv Preprint, 2025
Jiaxu Liu, Li Li, Hubert P. H. Shum and Toby P. Breckon
Topics: Generative AI
Webpage Cite This Plain Text
arXiv Preprint, 2025
Jiaxu Liu, Li Li, Hubert P. H. Shum and Toby P. Breckon
Topics: Generative AI
Webpage Cite This Plain Text
Jiaxu Liu, Li Li, Hubert P. H. Shum and Toby P. Breckon, "TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba," arXiv preprint arXiv:2503.13004, 2025.
Bibtex @article{liu25tfdm,
author={Liu, Jiaxu and Li, Li and Shum, Hubert P. H. and Breckon, Toby P.},
journal={arXiv},
title={TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba},
year={2025},
numpages={10},
eprint={arXiv:2503.13004},
archivePrefix={arXiv},
primaryClass={cs.CV},
doi={10.48550/arXiv.2503.13004},
url={https://arxiv.org/abs/2503.13004},
}
RIS author={Liu, Jiaxu and Li, Li and Shum, Hubert P. H. and Breckon, Toby P.},
journal={arXiv},
title={TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba},
year={2025},
numpages={10},
eprint={arXiv:2503.13004},
archivePrefix={arXiv},
primaryClass={cs.CV},
doi={10.48550/arXiv.2503.13004},
url={https://arxiv.org/abs/2503.13004},
}
TY - Preprint
AU - Liu, Jiaxu
AU - Li, Li
AU - Shum, Hubert P. H.
AU - Breckon, Toby P.
JO - arXiv preprints
SP - arXiv:2503.13004
KW - cs.CV
TI - TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba
PY - 2025
DO - 10.48550/arXiv.2503.13004
ER -
AU - Liu, Jiaxu
AU - Li, Li
AU - Shum, Hubert P. H.
AU - Breckon, Toby P.
JO - arXiv preprints
SP - arXiv:2503.13004
KW - cs.CV
TI - TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba
PY - 2025
DO - 10.48550/arXiv.2503.13004
ER -