IRR-RADA: A Reflection-Aware Saliency Map and Adaptive Curriculum Learning Based Data Augmentation Method for Image Reflection Removal

Wuyou Zhou, Fengshan Zhao, Yujie Wang, Qin Liu, Takeshi Ikenaga

Abstract: Mainstream image manipulation-based data augmentation methods undermine the integrity of extracted features, which limits their effectiveness for pixel-level image restoration tasks. In this paper, a reflection-specific data augmentation method, called IRR-RADA, for image reflection removal is proposed. Within it, the Reflection-Aware Saliency Map (RASM) accurately localizes reflection-affected regions by leveraging differential saliency effects, while the Adaptive Curriculum Learning (ACL) strategy gradually adjusts augmentation intensity based on reflection complexity and training stage. By integrating these two operations, the model is compelled to learn precise reflection removal while preserving the inherent structure of the target image. Experiments demonstrate that IRR-RADA achieves an average PSNR boost of 0.91dB compared to the baseline model without data augmentation.

External IDs:dblp:conf/mva/ZhouZWLI25