Reflective Gaussian Splatting

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yao, Yuxuan, Zeng, Zixuan, Gu, Chun, Zhu, Xiatian, Zhang, Li
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912216373002240
author Yao, Yuxuan
Zeng, Zixuan
Gu, Chun
Zhu, Xiatian
Zhang, Li
author_facet Yao, Yuxuan
Zeng, Zixuan
Gu, Chun
Zhu, Xiatian
Zhang, Li
contents Novel view synthesis has experienced significant advancements owing to increasingly capable NeRF- and 3DGS-based methods. However, reflective object reconstruction remains challenging, lacking a proper solution to achieve real-time, high-quality rendering while accommodating inter-reflection. To fill this gap, we introduce a Reflective Gaussian splatting (Ref-Gaussian) framework characterized with two components: (I) Physically based deferred rendering that empowers the rendering equation with pixel-level material properties via formulating split-sum approximation; (II) Gaussian-grounded inter-reflection that realizes the desired inter-reflection function within a Gaussian splatting paradigm for the first time. To enhance geometry modeling, we further introduce material-aware normal propagation and an initial per-Gaussian shading stage, along with 2D Gaussian primitives. Extensive experiments on standard datasets demonstrate that Ref-Gaussian surpasses existing approaches in terms of quantitative metrics, visual quality, and compute efficiency. Further, we show that our method serves as a unified solution for both reflective and non-reflective scenes, going beyond the previous alternatives focusing on only reflective scenes. Also, we illustrate that Ref-Gaussian supports more applications such as relighting and editing.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19282
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reflective Gaussian Splatting
Yao, Yuxuan
Zeng, Zixuan
Gu, Chun
Zhu, Xiatian
Zhang, Li
Computer Vision and Pattern Recognition
Novel view synthesis has experienced significant advancements owing to increasingly capable NeRF- and 3DGS-based methods. However, reflective object reconstruction remains challenging, lacking a proper solution to achieve real-time, high-quality rendering while accommodating inter-reflection. To fill this gap, we introduce a Reflective Gaussian splatting (Ref-Gaussian) framework characterized with two components: (I) Physically based deferred rendering that empowers the rendering equation with pixel-level material properties via formulating split-sum approximation; (II) Gaussian-grounded inter-reflection that realizes the desired inter-reflection function within a Gaussian splatting paradigm for the first time. To enhance geometry modeling, we further introduce material-aware normal propagation and an initial per-Gaussian shading stage, along with 2D Gaussian primitives. Extensive experiments on standard datasets demonstrate that Ref-Gaussian surpasses existing approaches in terms of quantitative metrics, visual quality, and compute efficiency. Further, we show that our method serves as a unified solution for both reflective and non-reflective scenes, going beyond the previous alternatives focusing on only reflective scenes. Also, we illustrate that Ref-Gaussian supports more applications such as relighting and editing.
title Reflective Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.19282