Research map / Vision-language and multimodal / Multimodal LLMs
Aligning Cross-View Visual Geometries in LVLMs Through Human-Like Reasoning Learning
Yuming Qiao, Liang Luo, Dan Meng, Yifan Yang, Qingyuan Wang, Juntuo Wang, Yuwei Zhang, Ru Zhen, Yanhao Zhang, Haonan Lu, Xudong Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Targets cross-view spatial reasoning in LVLMs, where prior work only handles single-frame 3D understanding; the abstract is truncated so the proposed method is not stated.
Problem
LVLMs struggle with consistent cross-view spatial reasoning, since existing methods inject 3D spatial concepts under a single coordinate system within one frame.
Approach
Abstract is truncated; the paper is said to align cross-view visual geometries via human-like reasoning learning, but the specific mechanism is not stated.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add human-like reasoning data (ablation) | SFT+RL CVVG-Reasoner · MV3DSR-Bench | camera pose: 0.384 -> 0.69 | Improved |
| add human-like reasoning data (ablation) | SFT+RL CVVG-Reasoner · MV3DSR-Bench | motion tracking: 0.571 -> 0.773 | Improved |
| add human-like reasoning data (ablation) | SFT+RL CVVG-Reasoner · MV3DSR-Bench | pose-aware shifts: 0.512 -> 0.588 | Improved |
| add human-like reasoning data (ablation) | SFT+RL CVVG-Reasoner · MV3DSR-Bench | cross-view grounding: 0.46 -> 0.45 | No clear effect |
| add RL stage after SFT (ablation) | CVVG-Reasoner · MV3DSR-Bench | camera pose: 0.392 -> 0.69 | Improved |
| add RL stage after SFT (ablation) | CVVG-Reasoner · MV3DSR-Bench | motion tracking: 0.484 -> 0.773 | Improved |
| add RL stage after SFT (ablation) | CVVG-Reasoner · MV3DSR-Bench | pose-aware shifts: 0.385 -> 0.588 | Improved |
| add RL stage after SFT (ablation) | CVVG-Reasoner · MV3DSR-Bench | cross-view grounding: 0.331 -> 0.45 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SpatialReasoner — SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning (NeurIPS 2025) · better on 9 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Limitations
- Full text unavailable; method details and results unknown
Closest papers by meaning
- Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs (AAAI 2026 · similarity 0.91)
- Learning Multi-View Spatial Reasoning from Cross-View Relations (CVPR 2026 · similarity 0.91)
- InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models (ICLR 2026 · similarity 0.91)
- SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning (NeurIPS 2025 · similarity 0.90)
- S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance (CVPR 2026 · similarity 0.90)
- Spatial Understanding from Videos: Structured Prompts Meet Simulation Data (NeurIPS 2025 · similarity 0.90)
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.
