Deep Adversarial Decomposition: A Unified Framework for Separating Superimposed Images

Zhengxia Zou, Sen Lei, Tianyang Shi, Zhenwei Shi, Jieping Ye; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 12806-12816

Abstract


Separating individual image layers from a single mixed image has long been an important but challenging task. We propose a unified framework named "deep adversarial decomposition" for single superimposed image separation. Our method deals with both linear and non-linear mixtures under an adversarial training paradigm. Considering the layer separating ambiguity that given a single mixed input, there could be an infinite number of possible solutions, we introduce a "Separation-Critic" - a discriminative network which is trained to identify whether the output layers are well-separated and thus further improves the layer separation. We also introduce a "crossroad L1" loss function, which computes the distance between the unordered outputs and their references in a crossover manner so that the training can be well-instructed with pixel-wise supervision. Experimental results suggest that our method significantly outperforms other popular image separation frameworks. Without specific tuning, our method achieves the state of the art results on multiple computer vision tasks, including the image deraining, photo reflection removal, and image shadow removal.

Related Material


[pdf] [supp] [video]
[bibtex]
@InProceedings{Zou_2020_CVPR,
author = {Zou, Zhengxia and Lei, Sen and Shi, Tianyang and Shi, Zhenwei and Ye, Jieping},
title = {Deep Adversarial Decomposition: A Unified Framework for Separating Superimposed Images},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}