OGG-FR: Orthogonal Gradient Gaming and Frequency Rectification for Unmanned Aerial Vehicle Infrared Image Super-Resolution
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors study how to improve the clarity of thermal images taken by drones using lightweight models, which is challenging because different training goals can give mixed signals. They introduce a new method called OGG-FR that cleverly separates and adjusts these mixed training signals to avoid confusion during learning. Their approach balances the contribution of pixel details and frequency information, leading to better super-resolution performance on thermal drone images. Experiments show that their method works well even when images are degraded or enlarged significantly.
Unmanned Aerial Vehicle (UAV)Infrared Image Super-ResolutionLightweight ModelsPixel-domain and Frequency-domain LossesGradient ConflictOrthogonal Gradient GamingFrequency RectificationMultiple Gradient Descent Algorithm (MGDA)High-frequency ResidualThermal Image Processing
Authors
Yongsong Huang, Qingzhong Wang, Xiaofeng Liu, Tomo Miyazaki, Yaohou Fan, Shinichiro Omachi
Abstract
Unmanned aerial vehicle (UAV) infrared image super-resolution aims to recover weak thermal structures for deployment on resource-constrained platforms; lightweight models are therefore preferred, but multi-loss training can be unstable. A common strategy combines pixel-domain and frequency-domain objectives; however, low contrast, limited high-frequency content, and sensor-specific noise often make their gradients weakly aligned or conflicting. To address this optimization ambiguity, we propose Orthogonal Gradient Gaming and Frequency Rectification (OGG-FR), a plug-and-play optimization framework that decomposes the frequency gradient into a redundant parallel component and an orthogonal innovation component relative to the pixel gradient. In the conflict regime, OGG-FR computes a safe base gradient using the Multiple Gradient Descent Algorithm (MGDA) and adds a variance-rectified orthogonal innovation; in the compatible regime, it discards redundant parallel information and injects the orthogonal innovation according to a confidence score estimated from the high-frequency residual. Experimental results on the UAV thermal benchmark show broad gains under BI and BD degradations at $\times 4$ and $\times 8$ scales, while gradient analyses support the effectiveness of the proposed conflict-aware update rule.