CamReasoner:通过结构化空间推理强化相机运动理解
CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning
AI总结:
CamReasoner通过结构化推理框架提升相机运动理解,采用O-T-A范式和大规模推理轨迹集,首次利用强化学习实现逻辑对齐,提升分类和VQA性能。
摘要:
理解相机动态是视频空间智能的基础支柱。然而,现有多模态模型大多将此任务视为黑盒分类,常依赖表面视觉模式而非几何线索来混淆物理上不同的运动。我们提出了CamReasoner框架,将相机运动理解重新表述为结构化推断过程,以弥合感知与电影逻辑之间的差距。我们的方法聚焦于观察-思考-回答(O-T-A)范式,迫使模型在显式推理块中阐述时空观察并推理解运动模式。为了培养这种能力,我们构建了一个包含18,000个SFT推理链和38,000个RL反馈样本的大规模推理轨迹集。到目前为止,我们首次在相机运动理解中使用强化学习实现逻辑对齐,确保运动推断基于结构化视觉推理而非上下文猜测。基于Qwen2.5-VL-7B,CamReasoner-7B在二分类准确率上从73.8%提升至78.4%,在VQA准确率上从60.9%提升至74.5%,在多个基准测试中持续优于专有和开源基线。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。