T$^2$exture: Sparsely Perturbed Thermal-to-Texture Imaging
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors propose a new method called T²exture to improve thermal images by capturing fine surface details that normal thermal cameras miss. Their approach uses a few moments with a special light on to reveal textures and many regular frames with the light off. By comparing these, they can reconstruct detailed thermal textures over time without needing a lot of extra data or complex equipment. Tests on both simulated and real data show their method recovers clearer textures and preserves structure better than existing methods.
thermal imaginglong-wave infrared (LWIR)thermal textureactive illuminationpassive measurementimage reconstructionvideo frame interpolationPSNRmaterial reflectancesparse perturbation
Authors
Jiashuo Chen, Cheng Dai, Yanan Hu, Fanglin Bao
Abstract
Thermal imaging remains effective under adverse illumination, yet passive long-wave infrared (LWIR) measurements often lack fine texture. Existing thermal texture imaging approaches commonly rely on spectral sensing or registered auxiliary modalities, incurring substantial data throughput or vulnerability to cross-modal degradation. We introduce T$^2$exture, a sparsely perturbed thermal texture imaging framework that aims to reconstruct temporally dense thermal texture sequences from densely sampled passive frames and a few actively perturbed keyframes. We define thermal texture as the residual between a source-on observation and its corresponding source-off passive state. Under sparse LWIR illumination and rapid quasi-steady paired acquisition, this residual attenuates the passive-emission background and approximates a source-induced reflected response, exposing localized material- and geometry-dependent texture. T$^2$exture reconstructs a dense sequence of this source-conditioned response through two stages. Stage 1 estimates the unobserved source-off passive state at each active instant from neighboring passive frames to obtain reliable differential texture anchors. Stage 2 combines sparse anchors with passive structural context near each target time to reconstruct the dense sequence. On the simulated benchmark, T$^2$exture adds only 0.20M parameters to AMT-L while improving PSNR by 6.66 dB. Extensive evaluations on simulated and real acquisitions further show clearer texture recovery and stronger structural preservation than representative VFI baselines. These results establish T$^2$exture as a practical framework for thermal texture imaging under sparse active acquisition.