SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Hanxiao, Gao, YuPeng, Xie, Jin, Yang, Jian, Wang, Beibei
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916681270427648
author Sun, Hanxiao
Gao, YuPeng
Xie, Jin
Yang, Jian
Wang, Beibei
author_facet Sun, Hanxiao
Gao, YuPeng
Xie, Jin
Yang, Jian
Wang, Beibei
contents Reconstructing 3D assets from images, known as inverse rendering (IR), remains a challenging task due to its ill-posed nature. 3D Gaussian Splatting (3DGS) has demonstrated impressive capabilities for novel view synthesis (NVS) tasks. Methods apply it to relighting by separating radiance into BRDF parameters and lighting, yet produce inferior relighting quality with artifacts and unnatural indirect illumination due to the limited capability of each Gaussian, which has constant material parameters and normal, alongside the absence of physical constraints for indirect lighting. In this paper, we present a novel framework called Spatially-vayring Gaussian Inverse Rendering (SVG-IR), aimed at enhancing both NVS and relighting quality. To this end, we propose a new representation-Spatially-varying Gaussian (SVG)-that allows per-Gaussian spatially varying parameters. This enhanced representation is complemented by a SVG splatting scheme akin to vertex/fragment shading in traditional graphics pipelines. Furthermore, we integrate a physically-based indirect lighting model, enabling more realistic relighting. The proposed SVG-IR framework significantly improves rendering quality, outperforming state-of-the-art NeRF-based methods by 2.5 dB in peak signal-to-noise ratio (PSNR) and surpassing existing Gaussian-based techniques by 3.5 dB in relighting tasks, all while maintaining a real-time rendering speed.
format Preprint
id arxiv_https___arxiv_org_abs_2504_06815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering
Sun, Hanxiao
Gao, YuPeng
Xie, Jin
Yang, Jian
Wang, Beibei
Computer Vision and Pattern Recognition
Reconstructing 3D assets from images, known as inverse rendering (IR), remains a challenging task due to its ill-posed nature. 3D Gaussian Splatting (3DGS) has demonstrated impressive capabilities for novel view synthesis (NVS) tasks. Methods apply it to relighting by separating radiance into BRDF parameters and lighting, yet produce inferior relighting quality with artifacts and unnatural indirect illumination due to the limited capability of each Gaussian, which has constant material parameters and normal, alongside the absence of physical constraints for indirect lighting. In this paper, we present a novel framework called Spatially-vayring Gaussian Inverse Rendering (SVG-IR), aimed at enhancing both NVS and relighting quality. To this end, we propose a new representation-Spatially-varying Gaussian (SVG)-that allows per-Gaussian spatially varying parameters. This enhanced representation is complemented by a SVG splatting scheme akin to vertex/fragment shading in traditional graphics pipelines. Furthermore, we integrate a physically-based indirect lighting model, enabling more realistic relighting. The proposed SVG-IR framework significantly improves rendering quality, outperforming state-of-the-art NeRF-based methods by 2.5 dB in peak signal-to-noise ratio (PSNR) and surpassing existing Gaussian-based techniques by 3.5 dB in relighting tasks, all while maintaining a real-time rendering speed.
title SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.06815