Model Releases
Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models
arXiv:2609.01059v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) tackle dynamic 3D spatial reasoning, ego-motion perception becomes essential to resolve monocular scale ambiguity. Howe
arXiv:2609.01059v1 Announce Type: new Abstract: 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 to rigorously decouple visual changes from true kinematic properties. Furthermore, we propose the TempoVista framework, featuring the Kinematic-GSPO algorithm. By embedding metric physical ground truth into policy optimization, TempoVista explicitly grounds visual representations in 3D space. Experiments demonstrate that our approach significantly improves both motion estimation and robust spatial reasoning by utilizing camera dynamics as an effective geometric calibration signal.
Related
- Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models
- SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments
- CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming
- Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment
Source: arXiv cs.CV | 2026-09-02