Q-CamTuning：面向直播摄像头调优的多模态大模型
Q-CamTuning: A Multimodal Large Language Model for Fine-Grained Quality Reasoning in Livestreaming Camera Tuning
直播画质调参这活儿有 AI 干了，这篇论文造了个能看图、找问题、直接告诉你怎么调摄像头参数的模型，IQA 方向的研究者可以看看。
论文提出 Q-CamTuning，一个用于直播场景摄像头自动调优的多模态大语言模型。作者构建了指令微调数据集 FGLive-Comments，包含图像对的细粒度偏好标注、全局与局部视觉证据的质量推理标注，并支持给出摄像头参数调整建议。模型采用渐进式感知-证据-引导框架，将质量问题映射到参数调整方向。实验显示 Q-CamTuning 在质量评分和细粒度图像对排序上超过现有 IQA 模型，用户研究也验证了其调参建议的有效性。
Q-CamTuning: A Multimodal Large Language Model for Fine-Grained Quality Reasoning in Livestreaming Camera Tuning
With the popularization of livestreaming applications, automatic camera tuning has become indispensable for ordinary users to enjoy high Quality of Experience (QoE). However, the existing Image Quality Assessment (IQA) methods face two challenges in camera tuning. First, they struggle to identify subtle quality difference between images, which is common in camera tuning. Second, the ability to explain fine-grained differences and to provide suggestions for camera tuning are even more lacking. To address these challenges, we first construct FGLive-Comments, an instruction tuning dataset with rich annotations of both preferences for fine-grained image pairs and quality reasoning from global and local visual evidence, which supports selective adjustment recommendations of camera parameters. Based on FGLive-Comments, we develop Q-CamTuning, a multimodal large language model for livestreaming camera tuning. Its progressive perception-evidence-guidance framework learns quality-aware visual representations, enhances fine-grained reasoning with global-local evidence, and maps quality issues to camera-parameter adjustment directions. Extensive experimental results demonstrate that Q-CamTuning outperforms existing IQA models in both quality scoring and fine-grained image pair ranking. User study also validates its ability to recommend camera tuning suggestions.