Papers
arxiv:2308.02963

Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models

Published on Aug 5, 2023
Authors:

Abstract

Diff-HMR uses a denoising diffusion process to generate multiple plausible 3D human body mesh reconstructions from 2D images, modeling the task's inherent ambiguity probabilistically.

AI-generated summary

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 single output. In contrast, we propose a generative approach framework, called "Diffusion-based Human Mesh Recovery (Diff-HMR)" that takes advantage of the denoising diffusion process to account for multiple plausible outcomes. During the training phase, the SMPL parameters are diffused from ground-truth parameters to random distribution, and Diff-HMR learns the reverse process of this diffusion. In the inference phase, the model progressively refines the given random SMPL parameters into the corresponding parameters that align with the input image. Diff-HMR, being a generative approach, is capable of generating diverse results for the same input image as the input noise varies. We conduct validation experiments, and the results demonstrate that the proposed framework effectively models the inherent ambiguity of the task of human mesh recovery in a probabilistic manner. The code is available at https://github.com/hanbyel0105/Diff-HMR

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2308.02963 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2308.02963 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2308.02963 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.