# Relighting

Physically based inverse rendering must separate materials from illumination, and the decomposition is ambiguous. Learned material predictions are usually added as auxiliary regularization losses, which change the objective and require rebalancing against photometric fitting. This work instead restricts the optimization space: multi-view material predictions are fused onto a mesh, a permutohedral lattice is built in the prior feature space, and surface points with similar predictions share material variables while the objective stays purely photometric. On Synthetic4Relight and TensoIR-Synthetic, relighting PSNR with two predictors is 1.5–2.5 dB above the strongest evaluated mesh-based baseline, and it beats a regularization loss using the same prior in controlled comparisons.

Physically based inverse rendering must separate materials from illumination, and the decomposition is ambiguous. Learned material predictions are usually added as auxiliary regularization losses, which change the objective and require rebalancing against photometric fitting. This work instead restricts the optimization space: multi-view material predictions are fused onto a mesh, a permutohedral lattice is built in the prior feature space, and surface points with similar predictions share material variables while the objective stays purely photometric. On Synthetic4Relight and TensoIR-Synthetic, relighting PSNR with two predictors is 1.5–2.5 dB above the strongest evaluated mesh-based baseline, and it beats a regularization loss using the same prior in controlled comparisons.

VolS-GS turns the spatial support of a Gaussian scene into an occupancy field on a coarse grid and runs a differentiable finite-volume light-transport solve on it, with a small network predicting per-Gaussian scattering and absorption coefficients so light can propagate through the object's interior; across three OLAT benchmarks it consistently improves relighting quality on held-out lights and views over GS3, SSS-GS, RNG, and SSD-GS.

VolS-GS turns the spatial support of a Gaussian scene into an occupancy field on a coarse grid and runs a differentiable finite-volume light-transport solve on it, with a small network predicting per-Gaussian scattering and absorption coefficients so light can propagate through the object's interior; across three OLAT benchmarks it consistently improves relighting quality on held-out lights and views over GS3, SSS-GS, RNG, and SSD-GS.