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

TL;DR

This paper introduces the first large-scale UHD image deraining dataset, benchmarks existing methods on UHD images, and proposes an efficient MLP-based model that outperforms state-of-the-art approaches in UHD image deraining.

Contribution

The paper provides a new UHD deraining dataset, conducts a comprehensive benchmark, and develops a novel, efficient MLP-based architecture tailored for UHD image deraining.

Findings

The UDR-Mixer outperforms existing methods in UHD deraining.

The dataset enables better evaluation of deraining methods on UHD images.

The proposed model maintains low complexity while achieving high performance.

Abstract

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.