ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zetong, Kaufmann, Manuel, Xue, Lixin, Song, Jie, Oswald, Martin R.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908325596102656
author Zhang, Zetong
Kaufmann, Manuel
Xue, Lixin
Song, Jie
Oswald, Martin R.
author_facet Zhang, Zetong
Kaufmann, Manuel
Xue, Lixin
Song, Jie
Oswald, Martin R.
contents Creating a photorealistic scene and human reconstruction from a single monocular in-the-wild video figures prominently in the perception of a human-centric 3D world. Recent neural rendering advances have enabled holistic human-scene reconstruction but require pre-calibrated camera and human poses, and days of training time. In this work, we introduce a novel unified framework that simultaneously performs camera tracking, human pose estimation and human-scene reconstruction in an online fashion. 3D Gaussian Splatting is utilized to learn Gaussian primitives for humans and scenes efficiently, and reconstruction-based camera tracking and human pose estimation modules are designed to enable holistic understanding and effective disentanglement of pose and appearance. Specifically, we design a human deformation module to reconstruct the details and enhance generalizability to out-of-distribution poses faithfully. Aiming to learn the spatial correlation between human and scene accurately, we introduce occlusion-aware human silhouette rendering and monocular geometric priors, which further improve reconstruction quality. Experiments on the EMDB and NeuMan datasets demonstrate superior or on-par performance with existing methods in camera tracking, human pose estimation, novel view synthesis and runtime. Our project page is at https://eth-ait.github.io/ODHSR.
format Preprint
id arxiv_https___arxiv_org_abs_2504_13167
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos
Zhang, Zetong
Kaufmann, Manuel
Xue, Lixin
Song, Jie
Oswald, Martin R.
Computer Vision and Pattern Recognition
I.4.5
Creating a photorealistic scene and human reconstruction from a single monocular in-the-wild video figures prominently in the perception of a human-centric 3D world. Recent neural rendering advances have enabled holistic human-scene reconstruction but require pre-calibrated camera and human poses, and days of training time. In this work, we introduce a novel unified framework that simultaneously performs camera tracking, human pose estimation and human-scene reconstruction in an online fashion. 3D Gaussian Splatting is utilized to learn Gaussian primitives for humans and scenes efficiently, and reconstruction-based camera tracking and human pose estimation modules are designed to enable holistic understanding and effective disentanglement of pose and appearance. Specifically, we design a human deformation module to reconstruct the details and enhance generalizability to out-of-distribution poses faithfully. Aiming to learn the spatial correlation between human and scene accurately, we introduce occlusion-aware human silhouette rendering and monocular geometric priors, which further improve reconstruction quality. Experiments on the EMDB and NeuMan datasets demonstrate superior or on-par performance with existing methods in camera tracking, human pose estimation, novel view synthesis and runtime. Our project page is at https://eth-ait.github.io/ODHSR.
title ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos
topic Computer Vision and Pattern Recognition
I.4.5
url https://arxiv.org/abs/2504.13167