TranSplat: Instant Object Relighting in Gaussian Splatting via Spherical Harmonic Radiance Transfer
Not on the map. Why?
Abstract (arXiv)
We present TranSplat, a method for instant, accurate object relighting within the Gaussian Splatting (GS) framework. Rather than relying on costly inverse rendering routines, we propose a BRDF-free radiance transfer strategy that analytically modulates the spherical harmonic (SH) appearance coefficients of an object's 2D Gaussian surfels using per-normal irradiance ratios derived from source and target environment maps. To handle view-dependent and glossy appearances without explicit material estimation, we introduce a specularity-aware dual-path SH transfer strategy that adapts higher-order SH bands in the reflection domain. Additionally, we propose a lightweight SH-domain self-shadowing module to ensure physically realistic occlusion without explicit mesh raycasting. Operating as a post-processing step, TranSplat requires no additional GS retraining for a pair of source and target scenes. Evaluations on synthetic and real-world objects demonstrate state-of-the-art accuracy, outperforming recent inverse-rendering and diffusion-based GS relighting methods across most conditions, all while completing relighting operations in under one second. Although bounded by radially symmetric BRDF approximations and the low-pass nature of the SH basis, TranSplat produces perceptually realistic renderings even for glossy, complex materials, establishing a valuable, lightweight path forward for GS relighting.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 45 references that are in the map. First posted on arXiv 28 Mar 2025.
Builds on
28 of 45 references.
References · 28
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2023Segment Anythingcited by 8,158
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
- 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
- 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 331
- 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 249
- 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 220
16 more
- 2023TensoIR: Tensorial Inverse Renderingcited by 166
- 2023Segment Any 3D Gaussianscited by 158
- 2021NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illuminationcited by 135
- 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 131
- 2023Relightable Gaussian Codec Avatarscited by 126
- 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
- 2022NeILF: Neural Incident Light Field for Physically-based Material Estimationcited by 105
- 2018InverseRenderNet: Learning single image inverse renderingcited by 100
- 2024Neural Gaffer: Relighting Any Object via Diffusioncited by 91
- 2023NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimationcited by 73
- 2020Crowdsampling the Plenoptic Functioncited by 62
- 2023Neural-PBIR Reconstruction of Shape, Material, and Illuminationcited by 45
- 2024IllumiNeRF: 3D Relighting Without Inverse Renderingcited by 29
- 2024LumiGauss: Relightable Gaussian Splatting in the Wildcited by 21
- 2024PRTGS: Precomputed Radiance Transfer of Gaussian Splats for Real-Time High-Quality Relightingcited by 17
- 2024ReCap: Better Gaussian Relighting with Cross-Environment Capturescited by 14
Built on by
Not cited yet.