Distribution-Aligned Diffusion for Human Mesh Recovery
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 infuses prior distribution information into the mesh distribution diffusion process, and provides useful prior knowledge to facilitate the mesh recovery task. Our method achieves state-of-the-art performance on three widely used datasets. Project page: https://gongjia0208.github.io/HMDiff/.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingHuman Mesh RecoveryMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models
This work focuses on the problem of reconstructing a 3D human body mesh from a given 2D image. Despite the inherent ambiguity of the task of human mesh recovery, most existing works have adopted a method of regressing a …
DenoisingHuman Mesh RecoveryLieHMR: Autoregressive Human Mesh Recovery with $SO(3)$ Diffusion
We tackle the problem of Human Mesh Recovery (HMR) from a single RGB image, formulating it as an image-conditioned human pose and shape generation. While recovering 3D human pose from 2D observations is inherently ambigu…
Human Mesh RecoveryDiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos
Human mesh recovery (HMR) provides rich human body information for various real-world applications. While image-based HMR methods have achieved impressive results, they often struggle to recover humans in dynamic scenari…
3D Human Pose EstimationHuman Mesh RecoveryEgocentric Whole-Body Human Mesh Recovery with Prior-Guided Learning
Egocentric human mesh recovery (HMR) from monocular head-mounted cameras is increasingly important for AR/VR applications, but remains challenging due to the lack of reliable ground-truth (GT) annotations based on parame…
Human Mesh RecoveryPose EstimationDPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
The recovery of occluded human meshes presents challenges for current methods due to the difficulty in extracting effective image features under severe occlusion. In this paper, we introduce DPMesh, an innovative framewo…
DenoisingHuman Mesh Recovery