AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors

Kang Du, Zhihao Liang, Yulin Shen, Zeyu Wang

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add diffusion normal priors (ablation)GS-ID · TensoIR SyntheticNVS PSNR: 37.962 -> 39.130Improved
add diffusion material priors (ablation)GS-ID · TensoIR SyntheticAlbedo PSNR: 29.585 -> 33.493Improved
add both normal and material priors (ablation)GS-ID · TensoIR SyntheticAlbedo PSNR: 29.101 -> 33.493Improved
add spherical Gaussian mixtures for local lighting (ablation)GS-ID · TensoIR SyntheticNVS PSNR: 36.670 -> 39.130Improved
add learnable environment map (ablation)GS-ID · TensoIR SyntheticNVS PSNR: 38.180 -> 39.130Improved
add per-splat shadow field (ablation)GS-ID · TensoIR SyntheticAlbedo PSNR: 30.280 -> 33.493Improved
use grid of 3^3 SGMs instead of a single SGM (ablation)GS-ID · TensoIR SyntheticNVS PSNR: 38.670 -> 39.130Improved
add SGMs to lighting model (ablation)GS-ID · TensoIR SyntheticNormal MAE: 5.916 -> 4.602Improved
remove environment map (ablation)GS-ID · TensoIR SyntheticNormal MAE: 4.701 -> 4.602Mixed
use deferred shading instead of forward shading (ablation)GS-ID · Mip-NeRF 360 (garden)training time: 299min -> 68minImproved
use CUDA implementation for deferred shading (ablation)GS-ID · Mip-NeRF 360 (garden)GPU memory: 36.8G -> 21.4GImproved
GS-ID instead of RelightGSGS-ID · ADT datasetAlbedo PSNR: 27.223 -> 29.133Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy