cs.CVNov 19, 2026

Less Than Meets the Eye: Action-Set Identifiability and Principled Abstention for 3D Physical Geometry

Authors: Reshad Ul Karim, Abrar Samin, Sammam Mahdi, Syeda Maliha Tabassum, Md Rashad Al Hasan Rony

Organizations: BRAC University · Deutsche Telekom AG

Abstract

A corridor, its mirror reflection, and its image on a display can look identical, yet their physical surfaces lie at different depths. We test whether bounded camera motions distinguish these explanations. Intervene3D takes an image and an initial geometry estimate, predicts the view under each hypothesis and candidate motion, and selects a motion by maximin separability. It reports the mechanism and first physical surface only if the available motions separate the hypotheses still in contention. Otherwise it abstains. An adequacy test also rejects observations that no hypothesis explains. On a matched synthetic benchmark with exact landmarks, disabling abstention gives confident answers on 76.4% of unresolvable scenes. With abstention, none receives a confident answer under exact or noisy landmarks. At 100% accuracy on answered scenes, maximin selection answers 61.0% of scenes and summed selection 43.1%. The adequacy test lowers wrong answers on strongly curved mirror scenes from 56.8% to 12.4%. Real display experiments compare two hypotheses using one frozen depth-network estimate. The second image supplies photometric evidence and is never passed through the depth network. One executed motion reduces the pooled median surface error of twelve networks by 31.5%. These networks have larger error inside the annotated panel than outside on 33.4% of illusion-benchmark images. They place the first physical surface behind the glass on 36.9% of Mirror3D frames.

Figures & tables

Appendix figures & tables30 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Geometry Beats Estimated Depth: RGB-Only Multi-Camera 3D Tracking under Sim2Real

    Aug 4, 2026Abdullah Naeem, Anav Katwal, Ayon Dey +2Synthetic-to-Real Domain Adaptation3D Point Tracking

  2. Depth Any Seen: Which Surfaces and How Far?

    Sep 25, 2026Xiaohao Xu, Xiaonan HuangDepth EstimationMetric Depth Estimation

  3. RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection

    Aug 10, 2026Zhihao Zhang, Gengwei Zhang, Tianlong Chen +13D Object DetectionMonocular 3D Object Detection