Score-Guided Diffusion for 3D Human Recovery

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Stathopoulos, Anastasis, Han, Ligong, Metaxas, Dimitris
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909137298784256
author Stathopoulos, Anastasis
Han, Ligong
Metaxas, Dimitris
author_facet Stathopoulos, Anastasis
Han, Ligong
Metaxas, Dimitris
contents We present Score-Guided Human Mesh Recovery (ScoreHMR), an approach for solving inverse problems for 3D human pose and shape reconstruction. These inverse problems involve fitting a human body model to image observations, traditionally solved through optimization techniques. ScoreHMR mimics model fitting approaches, but alignment with the image observation is achieved through score guidance in the latent space of a diffusion model. The diffusion model is trained to capture the conditional distribution of the human model parameters given an input image. By guiding its denoising process with a task-specific score, ScoreHMR effectively solves inverse problems for various applications without the need for retraining the task-agnostic diffusion model. We evaluate our approach on three settings/applications. These are: (i) single-frame model fitting; (ii) reconstruction from multiple uncalibrated views; (iii) reconstructing humans in video sequences. ScoreHMR consistently outperforms all optimization baselines on popular benchmarks across all settings. We make our code and models available at the https://statho.github.io/ScoreHMR.
format Preprint
id arxiv_https___arxiv_org_abs_2403_09623
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Score-Guided Diffusion for 3D Human Recovery
Stathopoulos, Anastasis
Han, Ligong
Metaxas, Dimitris
Computer Vision and Pattern Recognition
We present Score-Guided Human Mesh Recovery (ScoreHMR), an approach for solving inverse problems for 3D human pose and shape reconstruction. These inverse problems involve fitting a human body model to image observations, traditionally solved through optimization techniques. ScoreHMR mimics model fitting approaches, but alignment with the image observation is achieved through score guidance in the latent space of a diffusion model. The diffusion model is trained to capture the conditional distribution of the human model parameters given an input image. By guiding its denoising process with a task-specific score, ScoreHMR effectively solves inverse problems for various applications without the need for retraining the task-agnostic diffusion model. We evaluate our approach on three settings/applications. These are: (i) single-frame model fitting; (ii) reconstruction from multiple uncalibrated views; (iii) reconstructing humans in video sequences. ScoreHMR consistently outperforms all optimization baselines on popular benchmarks across all settings. We make our code and models available at the https://statho.github.io/ScoreHMR.
title Score-Guided Diffusion for 3D Human Recovery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.09623