Text2Thermal is a new framework that generates physics‑aware thermal images directly from textual descriptions. By providing thermally grounded captions that encode material properties, weather, time of day, and heat‑emission state, the method bypasses the need to infer unobservable radiometric factors from RGB images. It adapts a Stable Diffusion backbone to the thermal domain, optionally using a control signal for scene geometry, and achieves state‑of‑the‑art FID scores on M3FD, FLIR, and FMB datasets.
arXiv:2609.24531v1 Announce Type: new Abstract: Thermography plays a vital role in military and broader thermal analysis applications. Recent progress in 3D thermal reconstruction has extended temper...
arXiv:2607. 07962v1 Announce Type: cross Abstract: Inferring latent physical properties from sensory observations is a fundamental challenge in machine perception.
Thermography plays a vital role in military and broader thermal analysis applications. Recent progress in 3D thermal reconstruction has extended temperature analysis from 2D to 3D space, yet most exis...
Remote sensing vision-language models have advanced Earth observation understanding, but most existing work remains centered on RGB imagery, leaving the complementary information in infrared data underexplored. Infrared images provide distinctive cues, including thermal intensity structures, object boundaries, and illumination-invariant scene features, which can enrich visual-language learning beyond conventional RGB observations.
arXiv:2606. 17020v1 Announce Type: cross Abstract: Remote sensing vision-language models have advanced Earth observation understanding, but most existing work remains centered on RGB imagery, leaving the complementary information in infrared data underexplored.
arXiv:2601.15897v3 Announce Type: replace Abstract: Multi-modal scene reconstruction integrating RGB and thermal infrared data is essential for robust environmental perception across diverse lighting...
arXiv:2412. 02831v2 Announce Type: replace-cross Abstract: The increasing accessibility of radiometric thermal imaging sensors for unmanned aerial vehicles (UAVs) offers significant potential for advancing AI-driven aerial wildfire management.
arXiv:2607. 29445v1 Announce Type: cross Abstract: Infrared vision-language models (IR-VLMs) extend thermal perception to open-vocabulary classification, image captioning, and visual question answering.
The paper introduces SARTM, a framework that adapts the Segment Anything Model (SAM) for RGB‑thermal (RGB‑T) semantic segmentation. It fine‑tunes SAM with LoRA layers, incorporates language guidance, and employs a Cross‑Modal Knowledge Distillation module to bridge modality gaps. The approach also modifies the segmentation head and adds an auxiliary semantic head, achieving superior performance on MFNET, PST900, and FMB benchmarks.
Infrared-visible image fusion (IVIF) is pivotal for multimodal perception, yet reconciling the inherent information disparity between thermal and textural features remains a fundamental challenge. Existing prior-guided methods often rely on static constraints that induce optimization conflicts or utilize extrinsic semantic priors from large-scale foundation models (e.
The paper explores a synthetic-first training approach for detecting drones in medium- and long-wave infrared imagery, combining synthetic scene generation with fine-tuning on real data. It demonstrates that synthetic data can establish initial object representations, but real infrared data is crucial to close domain gaps and improve reliability. The study finds that aligning datasets has a greater impact on performance than increasing model size, and that semantic alignment in feature space is the strongest predictor of success, with radiometric factors like entropy and dynamic range also contributing.
The paper presents a systematic study of scientific image synthesis, comparing pixel‑based generation and programmatic approaches. It introduces ImgCoder, a logic‑driven framework that follows an "understand‑plan‑code" workflow to enhance structural precision, and SciGenBench, a benchmark that evaluates images for information utility and logical validity. The authors find that pixel‑based models exhibit systematic failure modes and that fine‑tuning large multimodal models on rigorously verified synthetic images consistently improves downstream reasoning performance.