T$^2$exture: Sparsely Perturbed Thermal-to-Texture Imaging

2026-08-03

AI Summary

This work addresses the lack of fine thermal texture in passive long-wave infrared (LWIR) imaging, a limitation that existing approaches often mitigate through multimodal or spectral sensing—strategies that incur high data overhead or suffer from cross-modal degradation. To overcome this, the paper proposes a novel paradigm that combines sparsely actuated keyframes with densely captured passive frames, enabling reconstruction of temporally continuous, high-density thermal texture sequences with minimal active excitation. The method defines thermal texture as the residual response between illuminated and unilluminated states and introduces a two-stage reconstruction framework: first estimating unobserved off-state frames from neighboring passive observations to establish texture anchors, then fusing these sparse anchors with structural context from passive frames to synthesize dense sequences. Experiments demonstrate that the approach improves PSNR by 6.66 dB on simulation benchmarks with only 0.20M additional parameters and consistently outperforms state-of-the-art video interpolation methods in both real-world and simulated settings, achieving superior texture clarity and structural fidelity.

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.

Problem

• thermal imaging
• texture recovery
• sparse perturbation
• LWIR
• thermal texture

Innovation

• thermal texture imaging
• sparse active perturbation
• differential thermal residual
• two-stage reconstruction
• LWIR reflectance