Distribution-Aligned Diffusion for Human Mesh Recovery

Lin Geng Foo, Jia Gong, Hossein Rahmani, Jun Liu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 9221-9232


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/.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Foo_2023_ICCV, author = {Foo, Lin Geng and Gong, Jia and Rahmani, Hossein and Liu, Jun}, title = {Distribution-Aligned Diffusion for Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9221-9232} }