Deep Image Deraining Via Intrinsic Rainy Image Priors and Multi-scale Auxiliary Decoding
Different rain models and novel network structures have been proposed to remove rain streaks from single rainy images. In this work, we bring attention to the intrinsic priors and multi-scale features of the rainy images, and develop several intrinsic loss functions to train a CNN deraining network. We first study the sparse priors of rainy images, which have been verified to preserve unbroken edges in image decomposition. However, its mathematical formulation usually leads to an intractable solution, we propose quasi-sparsity priors to decrease complexity, so that our network can be trained under the supervision of sparse properties of rainy images. Quasi-sparsity supervises network training in different gradient domain which is still ill-posed to decompose a rainy image into rain layer and background layer. We develop another $L_1$ loss based on the intrinsic low-value property of rain layer to restore image contents together with the commonly-used $L_1$ similarity loss. Multi-scale features are further explored via a multi-scale auxiliary decoding structure to show which kinds of features contribute the most to the deraining task, and the corresponding multi-scale auxiliary loss improves the deraining performance further. In our network, more efficient group convolution and feature sharing are utilized to obtain an one order of magnitude improvement in network running speed. The proposed deraining method performs favorably against state-of-the-art deraining approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Rain RemovalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-Decoding Deraining Network and Quasi-Sparsity Based Training
Existing deep deraining models are mainly learned via directly minimizing the statistical differences between rainy images and rain-free ground truths. They emphasize learning a mapping from rainy images to rain-free…
Rain RemovalUnsupervised Single Image Deraining with Self-supervised Constraints
Most existing single image deraining methods require learning supervised models from a large set of paired synthetic training data, which limits their generality, scalability and practicality in real-world multimedia app…
BenchmarkingGenerative Adversarial NetworkRain RemovalSingle Image DerainingUnpaired Photo-realistic Image Deraining with Energy-informed Diffusion Model
Existing unpaired image deraining approaches face challenges in accurately capture the distinguishing characteristics between the rainy and clean domains, resulting in residual degradation and color distortion within the…
Rain RemovalUnsupervised Deraining: Where Contrastive Learning Meets Self-similarity
Image deraining is a typical low-level image restoration task, which aims at decomposing the rainy image into two distinguishable layers: the clean image layer and the rain layer. Most of the existing learning-based dera…
Contrastive LearningImage RestorationRain RemovalUnsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity
Most of the existing learning-based deraining methods are supervisedly trained on synthetic rainy-clean pairs. The domain gap between the synthetic and real rain makes them less generalized to complex real rainy scenes. …
Contrastive LearningRain Removal