ROS-GS: Relightable Outdoor Scenes With Gaussian Splatting
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (9) , 1-17
Abstract
Image data captured outdoors often exhibit unbounded scenes and unconstrained, varying lighting conditions, making it challenging to decompose them into geometry, reflectance, and illumination. Recent works have focused on achieving this decomposition using Neural Radiance Fields (NeRF) or the 3D Gaussian Splatting (3DGS) representation but remain hindered by two key limitations: the high computational overhead associated with neural networks of NeRF and the use of lowfrequency lighting representations, which often result in inefficient rendering and suboptimal relighting accuracy. We propose ROSGS, a two-stage pipeline designed to efficiently reconstruct relightable outdoor scenes using the Gaussian Splatting representation. By leveraging monocular normal priors, ROS-GS first reconstructs the scene's geometry with the compact 2D Gaussian Splatting (2DGS) representation, providing an efficient and accurate geometric foundation. Building upon this reconstructed geometry, ROS-GS then decomposes the scene's texture and lighting through a hybrid lighting model. This model effectively represents typical outdoor lighting by employing a spherical Gaussian function to capture the directional, high-frequency components of sunlight, while learning a radiance transfer function via Spherical Harmonic coefficients to model the remaining lowfrequency skylight comprehensively. Both quantitative metrics and qualitative comparisons demonstrate that ROS-GS achieves state-of-the-art performance in relighting outdoor scenes and highlight its ability to deliver superior relighting accuracy and rendering efficiency.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62322210)
- Beijing Major Science and Technology Project (Z251100008125009)
- Innovation Funding of ICT, CAS (E561100)
- Beijing Natural Science Foundation (L242153)
This publication has 64 references indexed in Scilit:
- Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing2024
- The Sky’s the Limit: Relightable Outdoor Scenes via a Sky-Pixel Constrained Illumination Prior and Outside-In Visibility2024
- SWAG: Splatting in the Wild Images with Appearance-Conditioned Gaussians2024
- CityGaussian: Real-Time High-Quality Large-Scale Scene Rendering with Gaussians2024
- SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views2022
- NeRF for Outdoor Scene Relighting2022
- Deep Reflectance Volumes: Relightable Reconstructions from Multi-view Photometric Images2020
- Self-supervised Outdoor Scene Relighting2020
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation2019
- Occupancy Networks: Learning 3D Reconstruction in Function Space2019