回望过去：利用视觉语言模型从热迹中进行时间反转场景重建
See the past: Time-Reversed Scene Reconstruction from Thermal Traces Using Visual Language Models
AI总结：
本文提出利用视觉语言模型和约束扩散过程，从热迹中恢复过去几秒钟的场景状态，展示了时间反转成像的可行性。
摘要：
从当前观测中恢复过去是一个具有潜在应用在刑侦和场景分析中的挑战性问题。热成像在红外范围内工作，提供了原本不可见的信息。由于人类通常比周围环境温暖（37°C - 98.6°F），坐、触碰或倚靠等互动会留下残余的热量痕迹。这些逐渐消失的印记作为被动的时间代码，允许推断出超过普通RGB相机能力的近期事件。本文提出了一种时间反转重建框架，利用配对的RGB和热图像来从几秒钟前恢复场景状态。所提出的方法将视觉语言模型（VLMs）与约束扩散过程相结合，其中一个VLM生成场景描述，另一个引导图像重建，确保语义和结构的一致性。该方法在三个受控场景中进行了评估，证明了从热迹中恢复 plausible 的过去帧的可行性，为从热迹中实现时间反转成像提供了一个初步步骤。
英文摘要：
Recovering the past from present observations is an intriguing challenge with potential applications in forensics and scene analysis. Thermal imaging, operating in the infrared range, provides access to otherwise invisible information. Since humans are typically warmer (37 C -98.6 F) than their surroundings, interactions such as sitting, touching, or leaning leave residual heat traces. These fading imprints serve as passive temporal codes, allowing for the inference of recent events that exceed the capabilities of RGB cameras. This work proposes a time-reversed reconstruction framework that uses paired RGB and thermal images to recover scene states from a few seconds earlier. The proposed approach couples Visual-Language Models (VLMs) with a constrained diffusion process, where one VLM generates scene descriptions and another guides image reconstruction, ensuring semantic and structural consistency. The method is evaluated in three controlled scenarios, demonstrating the feasibility of reconstructing plausible past frames up to 120 seconds earlier, providing a first step toward time-reversed imaging from thermal traces.
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。
