Publications
Detailed Information
MCW-Net: Single image deraining with multi-level connections and wide regional non-local blocks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Yeachan | - |
dc.contributor.author | Jeon, Myeongho | - |
dc.contributor.author | Lee, Junho | - |
dc.contributor.author | Kang, Myungjoo | - |
dc.date.accessioned | 2022-06-21T08:29:02Z | - |
dc.date.available | 2022-06-21T08:29:02Z | - |
dc.date.created | 2022-05-31 | - |
dc.date.issued | 2022-07 | - |
dc.identifier.citation | Signal Processing: Image Communication, Vol.105, p. 116701 | - |
dc.identifier.issn | 0923-5965 | - |
dc.identifier.uri | https://hdl.handle.net/10371/182688 | - |
dc.description.abstract | A recent line of convolutional neural network-based works has succeeded in capturing rain streaks. However, difficulties in detailed recovery still remain. In this paper, we present a multi-level connection and wide regional non-local block network (MCW-Net) to properly restore the original background textures in rainy images. Unlike existing encoder-decoder-based image deraining models that improve performance with additional branches, MCW-Net improves performance by maximizing information utilization without additional branches through the following two proposed methods. The first method is a multi-level connection that repeatedly connects multi-level features of the encoder network to the decoder network. Multi-level connection encourages the decoding process to use the feature information of all levels. In multi-level connection, channel-wise attention is considered to learn which level of features is important in the decoding process of the current level. The second method is a wide regional non-local block. As rain streaks primarily exhibit a vertical distribution, we divide the grid of the image into horizontally-wide patches and apply a non-local operation to each region to explore the rich rain-free background information. Experimental results on both synthetic and real-world rainy datasets demonstrate that the proposed model significantly outperforms existing state-of-the-art models. Furthermore, the results of the joint deraining and segmentation experiment prove that our model contributes effectively to other vision tasks. | - |
dc.language | 영어 | - |
dc.publisher | Elsevier BV | - |
dc.title | MCW-Net: Single image deraining with multi-level connections and wide regional non-local blocks | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.image.2022.116701 | - |
dc.citation.journaltitle | Signal Processing: Image Communication | - |
dc.identifier.wosid | 000794236100004 | - |
dc.identifier.scopusid | 2-s2.0-85129546618 | - |
dc.citation.startpage | 116701 | - |
dc.citation.volume | 105 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Kang, Myungjoo | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.