AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction

Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu, Gim Hee Lee

ICML 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 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 Gaussian primitive truncation (ablation)AmbiSuR (PGSR base with depth prior) · Tanks and TemplesF1-score: 0.547 -> 0.558Improved
add ray-color consistency (ablation)AmbiSuR · Tanks and TemplesF1-score: 0.558 -> 0.566Improved
add SH ambiguity indication instead of naive uniform depth-normal loss (ablation)AmbiSuR · Tanks and TemplesF1-score: 0.557 -> 0.589Improved
use naive uniform depth-normal loss instead of SH indication (ablation)AmbiSuR with truncation and ray-color · Tanks and TemplesPrecision: 0.552 -> 0.533Hurt
add dual-end (upper and lower) indication (ablation)SH ambiguity indicator · DTUChamfer distance: 0.473 -> 0.461Improved
add amorphous mask (ablation)SH ambiguity indicator · DTUChamfer distance: 0.472 -> 0.461Improved
add parameter separation (ablation)SH ambiguity indicator · DTUChamfer distance: 0.470 -> 0.461Improved
truncation bound gamma 1.5 sigma instead of 2.0 sigma (ablation)Gaussian primitive truncation · Tanks and TemplesF1-score: 0.589 -> 0.574Hurt
no truncation (gamma infinite) versus gamma 2.0 (ablation)Gaussian primitive truncation · Tanks and TemplesF1-score: 0.576 -> 0.589Improved
vary upper/lower indicator sizes (90-98% and 5-15%) (ablation)Dual-end indication · DTUChamfer distance: 0.461 -> 0.463No clear effect
swap depth prior model (VGGT, MVSAnywhere, DepthPro, DA3, DAV2) (ablation)AmbiSuR · DTUChamfer distance: 0.468 (VGGT) vs 0.461 (DA3)No clear effect
use AmbiSuR instead of PGSR with same priors (ablation)PGSR baseline · DTUChamfer distance: 0.480 -> 0.461Improved

Earlier methods this paper compares with

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