Home > Research > Publications & Outputs > Distribution-Aligned Diffusion for Human Mesh R...

Electronic data

Links

Text available via DOI:

View graph of relations

Distribution-Aligned Diffusion for Human Mesh Recovery

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Distribution-Aligned Diffusion for Human Mesh Recovery. / Foo, Lin Geng; Gong, Jia; Rahmani, Hossein et al.
2023 IEEE/CVF International Conference on Computer Vision (ICCV). Institute of Electrical and Electronics Engineers Inc., 2024. p. 9187-9198 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Foo, LG, Gong, J, Rahmani, H & Liu, J 2024, Distribution-Aligned Diffusion for Human Mesh Recovery. in 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 9187-9198, 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, 2/10/23. https://doi.org/10.1109/ICCV51070.2023.00846

APA

Foo, L. G., Gong, J., Rahmani, H., & Liu, J. (2024). Distribution-Aligned Diffusion for Human Mesh Recovery. In 2023 IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 9187-9198). (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV51070.2023.00846

Vancouver

Foo LG, Gong J, Rahmani H, Liu J. Distribution-Aligned Diffusion for Human Mesh Recovery. In 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Institute of Electrical and Electronics Engineers Inc. 2024. p. 9187-9198. (Proceedings of the IEEE International Conference on Computer Vision). Epub 2023 Jun 1. doi: 10.1109/ICCV51070.2023.00846

Author

Foo, Lin Geng ; Gong, Jia ; Rahmani, Hossein et al. / Distribution-Aligned Diffusion for Human Mesh Recovery. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Institute of Electrical and Electronics Engineers Inc., 2024. pp. 9187-9198 (Proceedings of the IEEE International Conference on Computer Vision).

Bibtex

@inproceedings{524a7a7199594ef288944a826a9d1f48,
title = "Distribution-Aligned Diffusion for Human Mesh Recovery",
abstract = "Recovering a 3D human mesh from a single RGB image is a challenging task due to depth ambiguity and self-occlusion, resulting in a high degree of uncertainty. Meanwhile, diffusion models have recently seen much success in generating high-quality outputs by progressively denoising noisy inputs. Inspired by their capability, we explore a diffusion-based approach for human mesh recovery, and propose a Human Mesh Diffusion (HMDiff) framework which frames mesh recovery as a reverse diffusion process. We also propose a Distribution Alignment Technique (DAT) that injects input-specific distribution information into the diffusion process, and provides useful prior knowledge to simplify the mesh recovery task. Our method achieves state-of-the-art performance on three widely used datasets. Project page: https://gongjia0208.github.io/HMDiff/.",
author = "Foo, {Lin Geng} and Jia Gong and Hossein Rahmani and Jun Liu",
year = "2024",
month = jan,
day = "15",
doi = "10.1109/ICCV51070.2023.00846",
language = "English",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "9187--9198",
booktitle = "2023 IEEE/CVF International Conference on Computer Vision (ICCV)",
note = "2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 ; Conference date: 02-10-2023 Through 06-10-2023",

}

RIS

TY - GEN

T1 - Distribution-Aligned Diffusion for Human Mesh Recovery

AU - Foo, Lin Geng

AU - Gong, Jia

AU - Rahmani, Hossein

AU - Liu, Jun

PY - 2024/1/15

Y1 - 2024/1/15

N2 - Recovering a 3D human mesh from a single RGB image is a challenging task due to depth ambiguity and self-occlusion, resulting in a high degree of uncertainty. Meanwhile, diffusion models have recently seen much success in generating high-quality outputs by progressively denoising noisy inputs. Inspired by their capability, we explore a diffusion-based approach for human mesh recovery, and propose a Human Mesh Diffusion (HMDiff) framework which frames mesh recovery as a reverse diffusion process. We also propose a Distribution Alignment Technique (DAT) that injects input-specific distribution information into the diffusion process, and provides useful prior knowledge to simplify the mesh recovery task. Our method achieves state-of-the-art performance on three widely used datasets. Project page: https://gongjia0208.github.io/HMDiff/.

AB - Recovering a 3D human mesh from a single RGB image is a challenging task due to depth ambiguity and self-occlusion, resulting in a high degree of uncertainty. Meanwhile, diffusion models have recently seen much success in generating high-quality outputs by progressively denoising noisy inputs. Inspired by their capability, we explore a diffusion-based approach for human mesh recovery, and propose a Human Mesh Diffusion (HMDiff) framework which frames mesh recovery as a reverse diffusion process. We also propose a Distribution Alignment Technique (DAT) that injects input-specific distribution information into the diffusion process, and provides useful prior knowledge to simplify the mesh recovery task. Our method achieves state-of-the-art performance on three widely used datasets. Project page: https://gongjia0208.github.io/HMDiff/.

U2 - 10.1109/ICCV51070.2023.00846

DO - 10.1109/ICCV51070.2023.00846

M3 - Conference contribution/Paper

AN - SCOPUS:85171176631

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 9187

EP - 9198

BT - 2023 IEEE/CVF International Conference on Computer Vision (ICCV)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023

Y2 - 2 October 2023 through 6 October 2023

ER -