Event
CLEAR-IR Infrared Image Reconstruction Framework Released
1 reports · 1 sources
Nathan Shankar and other authors propose the CLEAR-IR framework, which reconstructs infrared images with structured-light emitter patterns into clean, RGB-style images, enabling vision pipelines originally trained on RGB to continue working under conditions with no visible light. The framework uses a dual-stream architecture and is inspired by DeepMAO. The authors evaluate it on object detection, ArUco marker detection, and visual SLAM, covering scenarios ranging from well-lit to complete darkness; the authors state that in complete darkness, passive RGB enhancement methods fail because the sensor has no signal. The paper has been accepted to IEEE/RSJ IROS 2026.
Report timeline
- CLEAR-IR: Reconstructing Infrared Images into RGB-Style Images to Support Robot Perception in Dark Environments
CLEAR-IR proposes a dual-stream architecture that reconstructs clean, RGB-style images from infrared images containing structured-light emitter patterns, allowing vision pipelines originally trained on RGB to keep working when no visible light is available. Inspired by DeepMAO, the architecture was evaluated on object detection, ArUco marker detection, and visual SLAM, covering scenarios ranging from well-lit to completely dark; in complete darkness, passive RGB enhancement methods fail because the sensor receives no signal. The paper has been accepted to IEEE/RSJ IROS 2026.
arXiv cs.RO ·