FlowIR: Depth-driven Rectified Flow for Resolving Thermal Ambiguity in Infrared Super-Resolution
Distinguishing different heat sources in low-resolution infrared (IR) images is inherently difficult, as multiple thermal emitters often collapse into ambiguous and overlapping responses. Existing super-resolution methods hallucinate structures from such ambiguous 2D evidence, leading to thermal drift, boundary merging, and unreliable restoration under infrared degradations. We propose FlowIR, a depth-driven rectified flow framework that resolves thermal ambiguity by injecting 3D geometric cues into the generation process. Pseudo-3D depth lifting and depth-guided 3D convolutions disentangle overlapping foreground objects, while cluster-wise inter-attention suppresses cross-source feature contamination. A Thermal-Geometry Consistency Loss further enforces geometric alignment during refinement. Built upon a lightweight rectified flow backbone, FlowIR restores IR images in only a few steps, producing sharply separated, degradation-robust, and geometrically faithful high-resolution results.
Authors
- Xingyue Zhu
- Zhiying Jiang
- Zhexi Min (ORCID: https://orcid.org/0009-0004-7175-4640)
- Yang Zou
- Xingyuan Li
- Qinyun Mei
- Jinyuan Liu
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-12
- DOI
- https://doi.org/10.48550/arxiv.2611.16269
- Primary Topic
- Advanced Image Processing Techniques
- Type
- preprint