Neural-Code PIFu: High-Fidelity Single Image 3D Human Reconstruction via Neural Code Integration

Ruizhi Liu, Paolo Remagnino and Hubert P. H. Shum
Proceedings of the 2024 International Conference on Pattern Recognition (ICPR), 2024

H5-Index: 68#

Neural-Code PIFu: High-Fidelity Single Image 3D Human Reconstruction via Neural Code Integration
# According to Google Scholar 2025

Abstract

We introduce neural-code PIFu, a novel implicit function for 3D human reconstruction, leveraging neural codebooks, our approach learns recurrent patterns in the feature space and reuses them to improve current features. Many existing methods predict normal maps from image feature space which easily overlook non-trivial features. Moreover, neglecting global geometric correlations restricted the use of repetitive features to improve the expressive power of current features. In this work, we propose neural-code PIFu, a novel framework that enhances initial features by fusing them with neural codes that are learned from the input features and geometric prior. It also models the global geometric correlation to facilitate the use of neural codes. Extensive experiments demonstrate that our method outperforms state-of-the-art (SoTA) PIFubased approaches by a large margin, and achieves comparable results to parametric-models-based methods without the use of auxiliary data.


Downloads


YouTube


Cite This Research

Plain Text

Ruizhi Liu, Paolo Remagnino and Hubert P. H. Shum, "Neural-Code PIFu: High-Fidelity Single Image 3D Human Reconstruction via Neural Code Integration," in ICPR '24: Proceedings of the 2024 International Conference on Pattern Recognition, Kolkata, India, 2024.

BibTeX

@inproceedings{liu24neuralcode,
 author={Liu, Ruizhi and Remagnino, Paolo and Shum, Hubert P. H.},
 booktitle={Proceedings of the 2024 International Conference on Pattern Recognition},
 series={ICPR '24},
 title={Neural-Code PIFu: High-Fidelity Single Image 3D Human Reconstruction via Neural Code Integration},
 year={2024},
 location={Kolkata, India},
}

RIS

TY  - CONF
AU  - Liu, Ruizhi
AU  - Remagnino, Paolo
AU  - Shum, Hubert P. H.
T2  - Proceedings of the 2024 International Conference on Pattern Recognition
TI  - Neural-Code PIFu: High-Fidelity Single Image 3D Human Reconstruction via Neural Code Integration
PY  - 2024
ER  - 


Supporting Grants


Similar Research

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", Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) Posters, 2019
Shanfeng Hu, Hubert P. H. Shum and Antonio Mucherino, "DSPP: Deep Shape and Pose Priors of Humans", Proceedings of the 2019 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG), 2019
Ziyi Chang, George Alex Koulieris and Hubert P. H. Shum, "3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models", Proceedings of the 2022 ACM Symposium on Virtual Reality Software and Technology (VRST), 2022
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", Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023

HomeGoogle ScholarYouTubeLinkedInTwitter/XGitHubORCIDResearchGateEmail
 
Print