Towards Ultra-High-Definition Image Deraining: A Benchmark and An Efficient Method

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Hongming, Chen, Xiang, Wu, Chen, Zheng, Zhuoran, Pan, Jinshan, Fu, Xianping
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914813424173056
author Chen, Hongming
Chen, Xiang
Wu, Chen
Zheng, Zhuoran
Pan, Jinshan
Fu, Xianping
author_facet Chen, Hongming
Chen, Xiang
Wu, Chen
Zheng, Zhuoran
Pan, Jinshan
Fu, Xianping
contents Despite significant progress has been made in image deraining, existing approaches are mostly carried out on low-resolution images. The effectiveness of these methods on high-resolution images is still unknown, especially for ultra-high-definition (UHD) images, given the continuous advancement of imaging devices. In this paper, we focus on the task of UHD image deraining, and contribute the first large-scale UHD image deraining dataset, 4K-Rain13k, that contains 13,000 image pairs at 4K resolution. Based on this dataset, we conduct a benchmark study on existing methods for processing UHD images. Furthermore, we develop an effective and efficient vision MLP-based architecture (UDR-Mixer) to better solve this task. Specifically, our method contains two building components: a spatial feature rearrangement layer that captures long-range information of UHD images, and a frequency feature modulation layer that facilitates high-quality UHD image reconstruction. Extensive experimental results demonstrate that our method performs favorably against the state-of-the-art approaches while maintaining a lower model complexity. The code and dataset will be available at https://github.com/cschenxiang/UDR-Mixer.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17074
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Ultra-High-Definition Image Deraining: A Benchmark and An Efficient Method
Chen, Hongming
Chen, Xiang
Wu, Chen
Zheng, Zhuoran
Pan, Jinshan
Fu, Xianping
Computer Vision and Pattern Recognition
Despite significant progress has been made in image deraining, existing approaches are mostly carried out on low-resolution images. The effectiveness of these methods on high-resolution images is still unknown, especially for ultra-high-definition (UHD) images, given the continuous advancement of imaging devices. In this paper, we focus on the task of UHD image deraining, and contribute the first large-scale UHD image deraining dataset, 4K-Rain13k, that contains 13,000 image pairs at 4K resolution. Based on this dataset, we conduct a benchmark study on existing methods for processing UHD images. Furthermore, we develop an effective and efficient vision MLP-based architecture (UDR-Mixer) to better solve this task. Specifically, our method contains two building components: a spatial feature rearrangement layer that captures long-range information of UHD images, and a frequency feature modulation layer that facilitates high-quality UHD image reconstruction. Extensive experimental results demonstrate that our method performs favorably against the state-of-the-art approaches while maintaining a lower model complexity. The code and dataset will be available at https://github.com/cschenxiang/UDR-Mixer.
title Towards Ultra-High-Definition Image Deraining: A Benchmark and An Efficient Method
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.17074