Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Yiqun, Wu, Chenming, Huang, Binbin, Zhi, Yihao, Zhao, Chen, Wang, Jingdong, Gao, Shenghua
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915539924811776
author Zhao, Yiqun
Wu, Chenming
Huang, Binbin
Zhi, Yihao
Zhao, Chen
Wang, Jingdong
Gao, Shenghua
author_facet Zhao, Yiqun
Wu, Chenming
Huang, Binbin
Zhi, Yihao
Zhao, Chen
Wang, Jingdong
Gao, Shenghua
contents Efficient and accurate reconstruction of a relightable, dynamic clothed human avatar from a monocular video is crucial for the entertainment industry. This paper presents SGIA (Surfel-based Gaussian Inverse Avatar), which introduces efficient training and rendering for relightable dynamic human reconstruction. SGIA advances previous Gaussian Avatar methods by comprehensively modeling Physically-Based Rendering (PBR) properties for clothed human avatars, allowing for the manipulation of avatars into novel poses under diverse lighting conditions. Specifically, our approach integrates pre-integration and image-based lighting for fast light calculations that surpass the performance of existing implicit-based techniques. To address challenges related to material lighting disentanglement and accurate geometry reconstruction, we propose an innovative occlusion approximation strategy and a progressive training approach. Extensive experiments demonstrate that SGIA not only achieves highly accurate physical properties but also significantly enhances the realistic relighting of dynamic human avatars, providing a substantial speed advantage. We exhibit more results in our project page: https://GS-IA.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15212
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video
Zhao, Yiqun
Wu, Chenming
Huang, Binbin
Zhi, Yihao
Zhao, Chen
Wang, Jingdong
Gao, Shenghua
Computer Vision and Pattern Recognition
Graphics
Efficient and accurate reconstruction of a relightable, dynamic clothed human avatar from a monocular video is crucial for the entertainment industry. This paper presents SGIA (Surfel-based Gaussian Inverse Avatar), which introduces efficient training and rendering for relightable dynamic human reconstruction. SGIA advances previous Gaussian Avatar methods by comprehensively modeling Physically-Based Rendering (PBR) properties for clothed human avatars, allowing for the manipulation of avatars into novel poses under diverse lighting conditions. Specifically, our approach integrates pre-integration and image-based lighting for fast light calculations that surpass the performance of existing implicit-based techniques. To address challenges related to material lighting disentanglement and accurate geometry reconstruction, we propose an innovative occlusion approximation strategy and a progressive training approach. Extensive experiments demonstrate that SGIA not only achieves highly accurate physical properties but also significantly enhances the realistic relighting of dynamic human avatars, providing a substantial speed advantage. We exhibit more results in our project page: https://GS-IA.github.io.
title Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2407.15212