FlowIR: Depth-driven Rectified Flow for Resolving Thermal Ambiguity in Infrared Super-Resolution

Xingyue Zhu, Qinyun Mei, Zhexi Min, Yang Zou, Xingyuan Li, Zhiying Jiang, Jinyuan Liu

Abstract

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.
BibTeX
@misc{zhu2026flowir,
  author = {Xingyue Zhu and Qinyun Mei and Zhexi Min and Yang Zou and Xingyuan Li and Zhiying Jiang and Jinyuan Liu},
  title = {{FlowIR: Depth-driven Rectified Flow for Resolving Thermal Ambiguity in Infrared Super-Resolution}},
  year = {2026},
  eprint = {2611.16269},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.16269},
}
Figure