Pretrained 3D Gaussian Splatting Scenes for ReLightGS: Relighting Existing 3D Gaussian Splatting Scenes Without Retraining

Pretrained 3D Gaussian Splatting (3DGS) scenes for ReLightGS, a real-time renderer that relights existing 3DGS scenes without retraining. Each archive <scene>.zip extracts into data/<scene>/ and contains: <scene>.ply (the trained Gaussians) <scene>.ply.labels.raw.bin (the per-Gaussian material cache) Scenes: lego, armadillo, ficus, hotdog (TensoIR-Synthetic) garden, bike, kitchen (Mip-NeRF 360) The Gaussians were trained with the original 3D Gaussian Splatting code (https://github.com/graphdeco-inria/gaussian-splatting) on the TensoIR-Synthetic and Mip-NeRF 360 datasets; please also cite those sources. Code and usage: https://github.com/KaanAres10/ReLightGS