ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning
Video spatial reasoning is essential for navigation-oriented perception and long-video question answering, where models must infer spatial relations across long horizons under changing viewpoints. However, existing multimodal large language models (MLLMs) remain largely semantic-centric, and often fail to reliably aggregate consistent spatial evidence from redundant video observations, leading to inefficient or unstable reasoning. To address these issues, we propose ConsiSpace, a geometry-consistency-aware framework for geometry-sensitive video spatial reasoning that turns spatial consistency into both an evidence organization principle and an explicit post-SFT learning signal. We build a...
| Authors | Ting Huang, Zhenyu Zhang, Wenyuan Huang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 20 July 2026 |
| Last updated at source | 20 July 2026 |
Models and datasets referencing this paper
- BAAI/ConsiSpaceModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.