Saved in:
Bibliographic Details
Main Authors: Wu, Hang, Cai, Yujun, Li, Zehao, Ge, Haonan, Sun, Bowen, Yuan, Junsong, Wang, Yiwei
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