We propose Multi-View Physical-prompt (MVP) for Test-Time Adaptation (TTA), a forward-only framework that moves TTA from tokens to photons by treating the camera exposure triangle (i.e., ISO, shutter speed, and aperture) as physical prompts. At inference, MVP acquires selected multiple physical views using a source-affinity score, evaluates digitally augmented variants of each retained view and filters the lowest-entropy predictions, and aggregates predictions with hard voting. This selection-then-vote design is simple, calibration-friendly, and requires no gradients or model modifications. On ImageNet-ES and ImageNet-ES-Diverse, MVP outperforms digital-only TTA on both Auto-Exposure and a combination with conventional sensor control. MVP remains effective under reduced parameter candidates that lower capture latency, demonstrating its practicality.

翻译：我们提出面向测试时自适应的多视角物理提示（MVP），这是一种仅需前向传播的框架，通过将相机曝光三角（即ISO、快门速度和光圈）作为物理提示，将测试时自适应从令牌层面推进至光子层面。在推理阶段，MVP利用源亲和度分数获取选定的多个物理视角，评估每个保留视角的数字增强变体并过滤最低熵预测，最后通过硬投票聚合预测结果。这种“先筛选后投票”的设计兼具简洁性与校准友好性，无需梯度计算或模型修改。在ImageNet-ES和ImageNet-ES-Diverse数据集上，MVP在自动曝光以及与传统传感器控制结合的任务中均优于纯数字测试时自适应方法。即便在减少候选参数（以降低采集延迟）的条件下，MVP仍保持有效性，证明了其实用性。