Joint Depth and Density Guided Single Image De-Raining

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

“…2) Hand-crafted Neural Network-based De-raining Methods: The major development of deep-learning-based deraining methods lies on the manual design of various neural networks [6], [24], [31]- [33], [38], [41], [43], [45], [45]- [47], [53]- [57]. In these de-raining networks, multi-scale architecture [6], [24], [26], [31], [32], [38], [41], [55], [60] and attention module [46], [54], [61] or their combination [33], [45], [56], [57] have been widely incorporated into the design of various image de-raining networks and have achieved the promising performance.…”

“…2) Hand-crafted Neural Network-based De-raining Methods: The major development of deep-learning-based deraining methods lies on the manual design of various neural networks [6], [24], [31]- [33], [38], [41], [43], [45], [45]- [47], [53]- [57]. In these de-raining networks, multi-scale architecture [6], [24], [26], [31], [32], [38], [41], [55], [60] and attention module [46], [54], [61] or their combination [33], [45], [56], [57] have been widely incorporated into the design of various image de-raining networks and have achieved the promising performance. The related works are succinctly described as follows: 1) Image de-raining using multi-scale neural networks: Wang et al [55] developed a modeling Haze-Like effect-based deep neural network for image de-raining, in which a SSP module [62] is introduced to extract multiscale features to help remove the haze-like effect.…”

“…of many outdoor vision systems [6]. In this context, image deraining becomes very necessary and meaningful, it can serve as an essential pre-step for various computer vision tasks such as object detection [7], object segmentation [8], autonomous driving [9], and more.…”

“…Over the past decade, a variety of successful algorithms, ranging from early hand-crafted prior-based methods [19]- [21], [27], [28] to the latest deep learning-based methods [6], [22]- [24], [26], [29]- [39], [41]- [47], [53]- [55], have been proposed to handle the image de-raining task. The priorbased de-raining methods first leverage effective regularizers to characterize the property of the background and rain streak layers, and then separate them by solving an objective function with proper optimization algorithms.…”

“…For deep learning-based de-raining methods, the major development over the years lies on the design of various effective neural network architectures. Among them, the multi-scale architecture [6], [24], [26], [31], [32], [38], [41], [55] and the attention module [43], [46], [47], [54], [56] or their combination [33], [45], [56], [57] have been demonstrated effective in boosting the performance. Take a few examples, Zhang et al [26] developed a multi-stream densely connected de-raining network to efficiently learn features at different scales.…”