Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Xiaoyuan, Zhao, Yizhou, Ye, Botao, Shan, Xiaojun, Lyu, Weijie, Qi, Lu, Chan, Kelvin C. K., Li, Yinxiao, Yang, Ming-Hsuan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.19291
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912446485102592
author Wang, Xiaoyuan
Zhao, Yizhou
Ye, Botao
Shan, Xiaojun
Lyu, Weijie
Qi, Lu
Chan, Kelvin C. K.
Li, Yinxiao
Yang, Ming-Hsuan
author_facet Wang, Xiaoyuan
Zhao, Yizhou
Ye, Botao
Shan, Xiaojun
Lyu, Weijie
Qi, Lu
Chan, Kelvin C. K.
Li, Yinxiao
Yang, Ming-Hsuan
contents We propose HoliGS, a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos. Unlike prior 4D Gaussian splatting and dynamic NeRF pipelines, which struggle with training overhead in minute-long captures, our method leverages invertible Gaussian Splatting deformation networks to reconstruct large-scale, dynamic environments accurately. Specifically, we decompose each scene into a static background plus time-varying objects, each represented by learned Gaussian primitives undergoing global rigid transformations, skeleton-driven articulation, and subtle non-rigid deformations via an invertible neural flow. This hierarchical warping strategy enables robust free-viewpoint novel-view rendering from various embodied camera trajectories by attaching Gaussians to a complete canonical foreground shape (\eg, egocentric or third-person follow), which may involve substantial viewpoint changes and interactions between multiple actors. Our experiments demonstrate that \ourmethod~ achieves superior reconstruction quality on challenging datasets while significantly reducing both training and rendering time compared to state-of-the-art monocular deformable NeRFs. These results highlight a practical and scalable solution for EVS in real-world scenarios. The source code will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19291
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
Wang, Xiaoyuan
Zhao, Yizhou
Ye, Botao
Shan, Xiaojun
Lyu, Weijie
Qi, Lu
Chan, Kelvin C. K.
Li, Yinxiao
Yang, Ming-Hsuan
Computer Vision and Pattern Recognition
We propose HoliGS, a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos. Unlike prior 4D Gaussian splatting and dynamic NeRF pipelines, which struggle with training overhead in minute-long captures, our method leverages invertible Gaussian Splatting deformation networks to reconstruct large-scale, dynamic environments accurately. Specifically, we decompose each scene into a static background plus time-varying objects, each represented by learned Gaussian primitives undergoing global rigid transformations, skeleton-driven articulation, and subtle non-rigid deformations via an invertible neural flow. This hierarchical warping strategy enables robust free-viewpoint novel-view rendering from various embodied camera trajectories by attaching Gaussians to a complete canonical foreground shape (\eg, egocentric or third-person follow), which may involve substantial viewpoint changes and interactions between multiple actors. Our experiments demonstrate that \ourmethod~ achieves superior reconstruction quality on challenging datasets while significantly reducing both training and rendering time compared to state-of-the-art monocular deformable NeRFs. These results highlight a practical and scalable solution for EVS in real-world scenarios. The source code will be released.
title HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.19291