AI RESEARCH
See the past: Time-Reversed Scene Reconstruction from Thermal Traces Using Visual Language Models
arXiv CS.AI
•
ArXi:2510.05408v2 Announce Type: replace-cross 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.