Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Huiling, Wu, Xianhao, Chen, Hongming
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.18124
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916263462174720
author Zhou, Huiling
Wu, Xianhao
Chen, Hongming
author_facet Zhou, Huiling
Wu, Xianhao
Chen, Hongming
contents Despite the superiority of convolutional neural networks (CNNs) and Transformers in single-image rain removal, current multi-scale models still face significant challenges due to their reliance on single-scale feature pyramid patterns. In this paper, we propose an effective rain removal method, the dual-path multi-scale Transformer (DPMformer) for high-quality image reconstruction by leveraging rich multi-scale information. This method consists of a backbone path and two branch paths from two different multi-scale approaches. Specifically, one path adopts the coarse-to-fine strategy, progressively downsampling the image to 1/2 and 1/4 scales, which helps capture fine-scale potential rain information fusion. Simultaneously, we employ the multi-patch stacked model (non-overlapping blocks of size 2 and 4) to enrich the feature information of the deep network in the other path. To learn a richer blend of features, the backbone path fully utilizes the multi-scale information to achieve high-quality rain removal image reconstruction. Extensive experiments on benchmark datasets demonstrate that our method achieves promising performance compared to other state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18124
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dual-Path Multi-Scale Transformer for High-Quality Image Deraining
Zhou, Huiling
Wu, Xianhao
Chen, Hongming
Computer Vision and Pattern Recognition
Despite the superiority of convolutional neural networks (CNNs) and Transformers in single-image rain removal, current multi-scale models still face significant challenges due to their reliance on single-scale feature pyramid patterns. In this paper, we propose an effective rain removal method, the dual-path multi-scale Transformer (DPMformer) for high-quality image reconstruction by leveraging rich multi-scale information. This method consists of a backbone path and two branch paths from two different multi-scale approaches. Specifically, one path adopts the coarse-to-fine strategy, progressively downsampling the image to 1/2 and 1/4 scales, which helps capture fine-scale potential rain information fusion. Simultaneously, we employ the multi-patch stacked model (non-overlapping blocks of size 2 and 4) to enrich the feature information of the deep network in the other path. To learn a richer blend of features, the backbone path fully utilizes the multi-scale information to achieve high-quality rain removal image reconstruction. Extensive experiments on benchmark datasets demonstrate that our method achieves promising performance compared to other state-of-the-art methods.
title Dual-Path Multi-Scale Transformer for High-Quality Image Deraining
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.18124