3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models

Ziyi Chang, George Alex Koulieris and Hubert P. H. Shum
Proceedings of the 2022 ACM Symposium on Virtual Reality Software and Technology (VRST), 2022

 Core A Conference

3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models
‡ According to Core Ranking 2023

Abstract

Acquiring the virtual equivalent of exhibits, such as sculptures, in virtual reality (VR) museums, can be labour-intensive and sometimes infeasible. Deep learning based 3D reconstruction approaches allow us to recover 3D shapes from 2D observations, among which single-view-based approaches can reduce the need for human intervention and specialised equipment in acquiring 3D sculptures for VR museums. However, there exist two challenges when attempting to use the well-researched human reconstruction methods: limited data availability and domain shift. Considering sculptures are usually related to humans, we propose our unsupervised 3D domain adaptation method for adapting a single-view 3D implicit reconstruction model from the source (real-world humans) to the target (sculptures) domain. We have compared the generated shapes with other methods and conducted ablation studies as well as a user study to demonstrate the effectiveness of our adaptation method. We also deploy our results in a VR application.


Downloads


YouTube


Cite This Research

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

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  - 


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
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 (VC), 2022
Naoki Nozawa, Hubert P. H. Shum, Edmond S. L. Ho and Shigeo Morishima, "3D Car Shape Reconstruction from a Single Sketch Image", 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, "Single Sketch Image Based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning", Proceedings of the 2020 International Conference on Computer Graphics Theory and Applications (GRAPP), 2020
Shanfeng Hu, Hubert P. H. Shum, Nauman Aslam, Frederick W. B. Li and Xiaohui Liang, "A Unified Deep Metric Representation for Mesh Saliency Detection and Non-Rigid Shape Matching", IEEE Transactions on Multimedia (TMM), 2020

 

Last updated on 6 October 2024
RSS Feed