TAP3D: Thermal-Assisted 3D Human Point Clouds

TAP3D is a new system that reconstructs dense 3D human point clouds from low‑cost thermal array sensors, avoiding the high cost, sparsity, and privacy issues of LiDAR, radar, and depth cameras. It uses a physics‑informed design with a forward thermal model, multi‑primitive estimation for self‑supervised depth recovery, and geometric perspective fusion to suppress interference and separate multiple people. The system, built on a single commodity sensor and evaluated on a 160K‑sample dataset, achieves high accuracy in downstream tasks such as fall detection, indoor tracking, and human mesh recovery.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• computer-vision
• safety