# T2exture: Sparsely Perturbed Thermal-to-Texture Imaging

arXiv: https://arxiv.org/abs/2608.02192 · HTML: https://mlsanity.com/paper/2608.02192/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 48 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion](https://mlsanity.com/paper/2211.14461/) (2022)
- [Video Frame Interpolation via Adaptive Separable Convolution](https://mlsanity.com/paper/1708.01692/) (2017)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [The 2018 PIRM Challenge on Perceptual Image Super-resolution](https://mlsanity.com/paper/1809.07517/) (2018)
- [DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion](https://mlsanity.com/paper/2303.06840/) (2023)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation](https://mlsanity.com/paper/2205.14620/) (2022)
- [Sparse Global Matching for Video Frame Interpolation with Large Motion](https://mlsanity.com/paper/2404.06913/) (2024)
- [BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions](https://mlsanity.com/paper/2412.11365/) (2024)
- [UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark](https://mlsanity.com/paper/2603.05075/) (2026)
- [Absorption-Based, Passive Range Imaging from Hyperspectral Thermal Measurements](https://mlsanity.com/paper/2308.05818/) (2023)
- [Hierarchical Flow Diffusion for Efficient Frame Interpolation](https://mlsanity.com/paper/2504.00380/) (2025)
- [Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers](https://mlsanity.com/paper/2601.14959/) (2026)
- [Universal computational thermal imaging overcoming the ghosting effect](https://mlsanity.com/paper/2604.01542/) (2026)
- [HADAR-Based Thermal Infrared Hyperspectral Image Restoration](https://mlsanity.com/paper/2605.13664/) (2026)
- [Ozone Cues Mitigate Reflected Downwelling Radiance in LWIR Absorption-Based Ranging](https://mlsanity.com/paper/2603.00273/) (2026)
- [TeX-1500: A Paired Real-World LWIR Hyperspectral Dataset and Benchmark for Temperature-Emissivity-Texture Decomposition](https://mlsanity.com/paper/2606.03806/) (2026)
- [Absorption-Feature-Guided Distance-Decoupled Estimation and Band Selection for LWIR Hyperspectral Passive Ranging](https://mlsanity.com/paper/2606.31824/) (2026)

## Abstract (arXiv)

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 T2exture, 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. T2exture 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, T2exture 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 T2exture as a practical framework for thermal texture imaging under sparse active acquisition.