Recursive residual atrous spatial pyramid pooling network for single image deraining

Li, Mengyao; Wang, Yongfang; Wang, Chuang

doi:10.1016/j.image.2021.116430

Cited by 5 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…recurrent architecture [19], [31], [32], [34], prior knowledgeguided model [2], [28], [48], generative network [1], [29], [40], [44], multi-scale pyramid [8], [16], [19], [38], [55], multistage learning [5], [21], [45], [47] and etc.. On the one hand, most synthetic datasets [7], [41], [49] for training the network do not consider veiling effect. And on the other hand, most existing methods [8], [16], [32], [38], [43] do not take detail reconstruction for rain removal into consideration.…”

Section: Related Workmentioning

confidence: 99%

From Heavy Rain Removal to Detail Restoration: A Faster and Better Network

Gao¹,

Wen²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

The dense rain accumulation in heavy rain can significantly wash out images and thus destroy the background details of images. Although existing deep rain removal models lead to improved performance for heavy rain removal, we find that most of them ignore the detail reconstruction accuracy of rain-free images. In this paper, we propose a dual-stage progressive enhancement network (DPENet) to achieve effective deraining with structure-accurate rain-free images. Two main modules are included in our framework, namely a rain streaks removal network (R 2 Net) and a detail reconstruction network (DRNet). The former aims to achieve accurate rain removal, and the latter is designed to recover the details of rain-free images. We introduce two main strategies within our networks to achieve trade-off between the effectiveness of deraining and the detail restoration of rain-free images. Firstly, a dilated dense residual block (DDRB) within the rain streaks removal network is presented to aggregate high/low level features of heavy rain. Secondly, an enhanced residual pixel-wise attention block (ERPAB) within the detail reconstruction network is designed for context information aggregation. We also propose a comprehensive loss function to highlight the marginal and regional accuracy of rainfree images. Extensive experiments on benchmark public datasets show both efficiency and effectiveness of the proposed method in achieving structure-preserving rain-free images for heavy rain removal. The source code and pre-trained models can be found at https://github.com/wybchd/DPENet.

show abstract

Section: Related Workmentioning

confidence: 99%

From Heavy Rain Removal to Detail Restoration: A Faster and Better Network

Gao¹,

Wen²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Multiscale information can be obtained by setting the dilated convolution to different dilation rates. The Atrous Spatial Pyramid Pooling (ASPP) module [20][21][22] is designed based on this idea in DeepLabV3 to merge multiscale context information. This module is also adopted in our designed model.…”

Section: Dilated Convolutionmentioning

confidence: 99%

Detection of Key Points in Mice at Different Scales via Convolutional Neural Network

Liu²,

Wang

et al. 2022

Symmetry

View full text Add to dashboard Cite

In this work, we propose a symmetry approach and design a convolutional neural network for mouse pose estimation under scale variation. The backbone adopts the UNet structure, uses the residual network to extract features, and adds the ASPP module into the appropriate residual units to expand the perceptual field, and uses the deep and shallow feature fusion to fuse and process the features at multiple scales to capture the various spatial relationships related to body parts to improve the recognition accuracy of the model. Finally, a set of prediction results based on heat map and coordinate offset is generated. We used our own built mouse dataset and obtained state-of-the-art results on the dataset.

show abstract