Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.00181 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918446271299584 |
|---|---|
| author | Wu, Hang Cai, Yujun Li, Zehao Ge, Haonan Sun, Bowen Yuan, Junsong Wang, Yiwei |
| author_facet | Wu, Hang Cai, Yujun Li, Zehao Ge, Haonan Sun, Bowen Yuan, Junsong Wang, Yiwei |
| contents | Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat this task as a black-box classification, often confusing physically distinct motions by relying on superficial visual patterns rather than geometric cues. We present \textbf{CamReasoner}, a framework that reformulates camera movement understanding as a structured inference process to bridge the gap between perception and cinematic logic. Our approach centers on the Observation-Thinking-Answer (O-T-A) paradigm, which compels the model to articulate spatio-temporal observations and reason about motion patterns within an explicit reasoning block. To instill this capability, we construct a Large-scale Inference Trajectory Suite comprising 18k SFT reasoning chains and 38k RL feedback samples. To the best of our knowledge, \textbf{we are the first to employ RL for logical alignment in camera movement understanding}, ensuring motion inferences are grounded in structured visual reasoning rather than contextual guesswork. Built upon Qwen2.5-VL-7B, CamReasoner-7B improves binary classification accuracy from 73.8\% to 78.4\% and VQA accuracy from 60.9\% to 74.5\% over its backbone, consistently outperforming both proprietary and open-source baselines across multiple benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00181 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning Wu, Hang Cai, Yujun Li, Zehao Ge, Haonan Sun, Bowen Yuan, Junsong Wang, Yiwei Computer Vision and Pattern Recognition Artificial Intelligence Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat this task as a black-box classification, often confusing physically distinct motions by relying on superficial visual patterns rather than geometric cues. We present \textbf{CamReasoner}, a framework that reformulates camera movement understanding as a structured inference process to bridge the gap between perception and cinematic logic. Our approach centers on the Observation-Thinking-Answer (O-T-A) paradigm, which compels the model to articulate spatio-temporal observations and reason about motion patterns within an explicit reasoning block. To instill this capability, we construct a Large-scale Inference Trajectory Suite comprising 18k SFT reasoning chains and 38k RL feedback samples. To the best of our knowledge, \textbf{we are the first to employ RL for logical alignment in camera movement understanding}, ensuring motion inferences are grounded in structured visual reasoning rather than contextual guesswork. Built upon Qwen2.5-VL-7B, CamReasoner-7B improves binary classification accuracy from 73.8\% to 78.4\% and VQA accuracy from 60.9\% to 74.5\% over its backbone, consistently outperforming both proprietary and open-source baselines across multiple benchmarks. |
| title | CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2602.00181 |