AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GUS-IR: Gaussian Splatting With Unified Shading for Inverse Rendering

Zhihao Liang, Hongdong Li, Kui Jia, Kailing Guo, Qi Zhang

TPAMI 2025 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS

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 deferred shading branch to forward shading (unified shading) (ablation)GUS-IR forward-only · Glossy BlenderPSNR: 28.64 -> 29.44Improved
add forward shading branch to deferred-only training (unified shading) (ablation)GUS-IR deferred-only · TensoIRPSNR: 36.35 -> 37.61Improved
add deferred shading to forward-only (ablation)GUS-IR forward-only · TensoIRPSNR: 37.74 -> 37.61Hurt
add deferred shading to forward-only (ablation)GUS-IR forward-only · Glossy BlenderLPIPS: 0.084 -> 0.057Improved
add deferred shading to forward-only (ablation)GUS-IR forward-only · Shiny BlenderPSNR: 33.15 -> 34.28Improved
use shortest-axis normal instead of attached learnable normal (ablation)Attach Normal · TensoIR relightingPSNR: 26.12 -> 27.53Improved
use shortest-axis normal instead of attached learnable normal (ablation)Attach Normal · TensoIRMAE: 5.433 -> 4.485Improved
use shortest-axis normal instead of residual normal (ablation)Residual Normal · Glossy Blender relightingPSNR: 24.72 -> 25.17Improved
use shortest-axis normal instead of attached normal (ablation)Attach Normal · Mip-NeRF 360 OutdoorPSNR: 23.89 -> 23.76Hurt
add indirect illumination and ambient occlusion modeling (ablation)GUS-IR without indirect · Mip-NeRF 360 IndoorPSNR: 28.52 -> 28.98Improved
add indirect illumination and ambient occlusion modeling (ablation)GUS-IR without indirect · TensoIRPSNR: 37.37 -> 37.61Improved
add indirect illumination and ambient occlusion modeling (ablation)GUS-IR without indirect · Shiny BlenderMAE: 2.193 -> 2.193No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 4 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