Benchmarking Ultra-High-Definition Image Reflection Removal
Zhenyuan Zhang, Zhenbo Song, Kaihao Zhang, Zhaoxin Fan, Jianfeng Lu

TL;DR
This paper introduces large-scale UHD datasets for single image reflection removal, evaluates existing methods on these datasets, and proposes a transformer-based model, RRFormer, achieving state-of-the-art results.
Contribution
The paper creates the first large-scale UHD datasets for SIRR, conducts comprehensive evaluation of existing methods, and proposes a novel transformer-based architecture for improved reflection removal.
Findings
Existing methods have limitations on UHD images.
RRFormer outperforms previous models on UHD datasets.
The datasets facilitate future UHD SIRR research.
Abstract
Deep learning based methods have achieved significant success in the task of single image reflection removal (SIRR). However, the majority of these methods are focused on High-Definition/Standard-Definition (HD/SD) images, while ignoring higher resolution images such as Ultra-High-Definition (UHD) images. With the increasing prevalence of UHD images captured by modern devices, in this paper, we aim to address the problem of UHD SIRR. Specifically, we first synthesize two large-scale UHD datasets, UHDRR4K and UHDRR8K. The UHDRR4K dataset consists of and quadruplets of images for training and testing respectively, and the UHDRR8K dataset contains and quadruplets. To the best of our knowledge, these two datasets are the first largest-scale UHD datasets for SIRR. Then, we conduct a comprehensive evaluation of six state-of-the-art SIRR methods using the proposed…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Advanced Image Processing Techniques · Image Processing Techniques and Applications
