paper-with-me

Papers

Phys3DGS: Physically-based 3D Gaussian Splatting for Inverse Rendering

2024-09-16 · Euntae Choi, Sungjoo Yoo

We propose two novel ideas (adoption of deferred rendering and mesh-based representation) to improve the quality of 3D Gaussian splatting (3DGS) based inverse rendering. We first report a problem incurred by hidden Gaussians, where Gaussians beneath the surface adversely affect the pixel color in the volume rendering adopted by the existing methods. In order to resolve the problem, we propose applying deferred rendering and report new problems incurred in a naive application of deferred rendering to the existing 3DGS-based inverse rendering. In an effort to improve the quality of 3DGS-based inverse rendering under deferred rendering, we propose a novel two-step training approach which (1) exploits mesh extraction and utilizes a hybrid mesh-3DGS representation and (2) applies novel regularization methods to better exploit the mesh. Our experiments show that, under relighting, the proposed method offers significantly better rendering quality than the existing 3DGS-based inverse rendering methods. Compared with the SOTA voxel grid-based inverse rendering method, it gives better rendering quality while offering real-time rendering.

📄 PDF Abstract BibTeX arXiv:2409.10335

Code (0)

등록된 구현이 없습니다.

Tasks

3DGSInverse Rendering

Methods 이 논문이 사용한 방법론

Report a Problem 설명 없음

Similar Papers 제목 키워드 기반

GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering

2024-10-31 · Kai Ye, Chong Gao, Guanbin Li, Wenzheng Chen 외

We consider the problem of physically-based inverse rendering using 3D Gaussian Splatting (3DGS) representations. While recent 3DGS methods have achieved remarkable results in novel view synthesis (NVS), accurately captu…

3DGSDisentanglementInverse RenderingNovel View Synthesis

Radiometrically Consistent Gaussian Surfels for Inverse Rendering

2026-03-02 · Kyu Beom Han, Jaeyoon Kim, Woo Jae Kim, Jinhwan Seo 외 arxiv

Inverse rendering with Gaussian Splatting has advanced rapidly, but accurately disentangling material properties from complex global illumination effects, particularly indirect illumination, remains a major challenge. Ex…

Computational EfficiencyInverse Rendering

OMG: Opacity Matters in Material Modeling with Gaussian Splatting

2025-02-16 · Silong Yong, Venkata Nagarjun Pudureddiyur Manivannan, Bernhard Kerbl, Zifu Wan 외

Decomposing geometry, materials and lighting from a set of images, namely inverse rendering, has been a long-standing problem in computer vision and graphics. Recent advances in neural rendering enable photo-realistic an…

Inverse RenderingNeural RenderingNovel View Synthesis

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

2025-04-09 · CVPR 2025 1 · Hanxiao Sun, Yupeng Gao, Jin Xie, Jian Yang 외

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 synthesi…

3DGSInverse RenderingNeRFNovel View Synthesis

Progressive Radiance Distillation for Inverse Rendering with Gaussian Splatting

2024-08-14 · Keyang Ye, Qiming Hou, Kun Zhou

We propose progressive radiance distillation, an inverse rendering method that combines physically-based rendering with Gaussian-based radiance field rendering using a distillation progress map. Taking multi-view images …

Inverse RenderingNovel View Synthesis