AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Geometric Collapse: When Vision Models Fail to Verify Physical Causality

Wentao Zhang, Jinhu Qi, Weiqiang Jin, Yifei Zhang, Chan-Tong Lam, Irwin King

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 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
violate occlusion causality (Direction cue) in edge perturbation (ablation)MiDaS DPT · NYU Depth v2 (N=1449)collapse ratio vs high-pass noise: 2.22x vs 1.00x for edge-shaped noiseHurt
violate occlusion causality (Direction cue) (ablation)DepthAnything V2 · NYU Depth v2 (N=1449)collapse ratio vs high-pass noise: 3.18xHurt
apply structure-only edge-shaped noise (ablation)DepthAnything V2 · NYU Depth v2 (N=1449)collapse ratio vs high-pass noise: 1.71xMixed
place noise in the scrambled mask without edge structure (ablation)all four depth models · NYU Depth v2 (N=1449)collapse ratio vs high-pass noise: 0.58x, 0.60x, 0.43x, 0.53xNo clear effect
combine all prior violations (Scrambled Edges) versus Direction only (ablation)DepthAnything V2 · NYU Depth v2 (N=1449)collapse ratio vs high-pass noise: 3.18x -> 3.20xImproved
increase perturbation intensity alpha from 0.2 to 0.8 (ablation)MiDaS DPT · NYU Depth v2 (N=1449)collapse ratio vs high-pass noise: 1.37x -> 2.34xImproved
increase number of edge segments K from 5 to 20 (ablation)MiDaS DPT · NYU Depth v2 (N=1449)collapse ratio vs high-pass noise: 2.10x -> 2.39xImproved
swap feed-forward estimator for diffusion (Marigold)depth estimator · NYU Depth v2 (N=1449)collapse ratio vs high-pass noise: 2.34x -> 1.55xImproved
swap feed-forward estimator for flow matching (DepthFM)depth estimator · NYU Depth v2 (N=1449)collapse ratio vs high-pass noise: 2.34x -> 1.11xImproved
oracle knowledge of perturbed pixels at the output instead of the inputMiDaS DPT · NYU Depth v2 (N=1449)recovery (%): 99.96% -> 47.0%Hurt
inpaint with oracle mask at input versus outputMiDaS DPT · NYU Depth v2 (N=1449)recovery (%): 24.0% vs 21.0%Mixed
add edge-consistency post-hoc defenseDepthAnything V2 · NYU Depth v2 (N=1449)recovery (%): 0.2252 -> 0.1560 RMSE vs clean; 26.4% recoveryImproved

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