AI Paper Atlas

Research map / 3D vision / Gaussian splatting

DR-GS: Physically-Based Deformable and Relightable 2D Gaussians

Jiaxin LI, Tong Wu, Yi Wei, Tailin Wu, Li Zhang

ECCV 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 0 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 learnable normal offset d to Gaussian attributes (ablation)DR-GS · mesh-driven rendering with extracted meshvisual qualityImproved
add learnable opacity alpha to Gaussian attributes (ablation)DR-GS · mesh-driven rendering with extracted meshvisual qualityImproved
add denoiser, MIS and mesh acceleration (ablation)DR-GS · Armadillorendering time and PSNRImproved
use particle-driven instead of mesh-driven variantDR-GS · GlossySynthetic angel (static reconstruction)PSNR: 25.04 -> 29.64Improved
use particle-driven instead of mesh-driven variantDR-GS · GlossySynthetic horse (static reconstruction)PSNR: 21.25 -> 25.54Improved
use DR-GS instead of GSP on angelGSP · GlossySynthetic angel (static reconstruction)PSNR: 25.70 -> 29.64Improved
use DR-GS instead of GSP on horseGSP · GlossySynthetic horse (static reconstruction)PSNR: 25.90 -> 25.54Hurt
use DR-GS instead of GS-ROR2 for relighting on angelGS-ROR2 · GlossySynthetic angel (relighting)PSNR: 20.81 -> 24.15Improved
use DR-GS instead of GS-ROR2 for relighting on tbellGS-ROR2 · GlossySynthetic tbell (relighting)PSNR: 22.80 -> 22.12Hurt
use DR-GS instead of GSP after relightingGSP · User study (deformation)Physical plausibility: 3.82 -> 4.62Improved
use DR-GS instead of PhysGaussianPhysGaussian · User study (deformation)Physical plausibility: 3.26 -> 4.56Improved

Later papers that compared with this method

2 later accepted papers report DRGS as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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