AI Paper Atlas

Research map / 3D vision / 3D generation

Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R

Zihao Zhu, Wenyuan Zhao, Nuo Chen, Chao Tian, Zhiwen Fan

ICML 2026 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 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
replace MASt3R confidence with evidential NIW uncertainty headMASt3R · ScanNet++AURC: 0.1649 -> 0.1233Improved
replace MASt3R confidence with evidential NIW uncertainty headMASt3R · ScanNet++Spearman rho: 0.2837 -> 0.4930Improved
replace MASt3R confidence with evidential NIW uncertainty headMASt3R · KITTIAURC: 1.0277 -> 0.9868Improved
evidential head versus single-pass heteroscedastic regressionMASt3R · KITTIAURC: 0.9749 -> 0.9868Hurt
add gated residual mean refinement (ablation)Trust3R · ScanNet++AURC: 0.1788 -> 0.1349Improved
add gated residual mean refinement (ablation)Trust3R · KITTIMAE: 1.6108 -> 1.6436Hurt
add gated residual mean refinement (ablation)Trust3R · KITTIAURC: 1.1170 -> 0.9942Improved
use full-covariance NIW head instead of factorized NIG (ablation)Trust3R · ETH3DAURC: 0.3213 -> 0.3040Improved
use full-covariance NIW head instead of factorized NIG (ablation)Trust3R · ScanNet++AURC: 0.1237 -> 0.1233No clear effect
use epistemic readout instead of aleatoric (ablation)Trust3R · ETH3DAURC: 0.3175 -> 0.3040Improved
use total uncertainty instead of aleatoric (ablation)Trust3R · ETH3DAURC: 0.3175 -> 0.3064Improved
attach evidential head to VGGT backboneVGGT · uncertainty rankingAUSE: 0.0452 -> 0.0209Improved

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