GHPT: Real-Time Relightable Gaussian Splatting using Hybrid Path Tracing
Jinyang Bo, Fan Dou, Wenrui Quan, Shangxun Liu, Yang Xu, Yuhe Zhang, Kang Li, Guohua Geng
摘要
3D Gaussian splatting (3DGS) has emerged as a promising approach for high-fidelity 3D scene representation. However, relighting and composition of Gaussian splatting remain challenging because path tracing is not directly applicable. Existing relighting methods for Gaussian splatting typically adopt either approximate rendering formulations or rely on Gaussian ray tracing, yielding low relighting performance and low rendering efficiency. To address these limitations, we propose Gaussian hybrid path tracing (GHPT), a threestage framework to acquire relightable Gaussian splatting models. The first stage utilizes planar-based Gaussian splatting reconstruction representation (PGSR) to enable multiview consistent depth rendering and reconstruct the surface mesh of a scene. The second stage performs physically-based differentiable rendering on the obtained mesh to reconstruct the material maps and the environment map. The third stage utilizes factorized inverse path tracing (FIPT) on the Gbuffer rendered by the PGSR, and visibility and indirect illumination are evaluated by hardware-accelerated ray tracing on the mesh with the material maps and the environment map reconstructed in the second stage. Experiments demonstrate that the relighting performance of GHPT outperforms the baselines, and our method can perform real-time relighting and composition of Gaussian splatting.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper22
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt 等NeurIPS 2021 · 被引用 2,500 次
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan 等CVPR 2022 · 被引用 1,603 次
- KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPsChristian Reiser, Songyou Peng, Yiyi Liao, Andreas GeigerICCV 2021 · 被引用 963 次
相关 Paper
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse RenderingHongze Chen, Zehong Lin, Jun ZhangICLR 2025
- IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray TracingChun Gu, Xiaofei Wei, Zixuan Zeng, Yuxuan Yao 等CVPR 2025
- GS-IR: 3D Gaussian Splatting for Inverse RenderingZhihao Liang, Qi Zhang, Ying Feng, Ying Shan 等CVPR 2024
- GS-2DGS: Geometrically Supervised 2DGS for Reflective Object ReconstructionJinguang Tong, Xuesong Li, Fahira Afzal Maken, Sundaram Muthu 等CVPR 2025
- Stochastic Ray Tracing for the Reconstruction of 3D Gaussian SplattingPeiyu Xu, Shuang Zhao, Xin Sun, Krishna Mullia 等CVPR 2026 · 被引用 1 次
