SOURCE-LINKED INTELLIGENCE

Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

As Vision-Language Models (VLMs) tackle dynamic 3D spatial reasoning, ego-motion perception becomes essential to resolve monocular scale ambiguity. However, current models often overfit to smooth trajectory priors rather than genuinely understanding physical motion. Consequently, their spatial reasoning degrades severely under large displacements, a phenomenon we term Kinematic Collapse. This failure stems from spurious visual-motion correlations in natural videos and a lack of explicit physical supervision. To evaluate this, we introduce Dyn-3D, a benchmark using counterfactual 3D rendering t

Read original source ↗ Open in workspace

recordType

paper

region

Global