Reversible Decoupling Network for Single Image Reflection Removal

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhao, Hao, Li, Mingjia, Hu, Qiming, Guo, Xiaojie
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916667194343424
author Zhao, Hao
Li, Mingjia
Hu, Qiming
Guo, Xiaojie
author_facet Zhao, Hao
Li, Mingjia
Hu, Qiming
Guo, Xiaojie
contents Recent deep-learning-based approaches to single-image reflection removal have shown promising advances, primarily for two reasons: 1) the utilization of recognition-pretrained features as inputs, and 2) the design of dual-stream interaction networks. However, according to the Information Bottleneck principle, high-level semantic clues tend to be compressed or discarded during layer-by-layer propagation. Additionally, interactions in dual-stream networks follow a fixed pattern across different layers, limiting overall performance. To address these limitations, we propose a novel architecture called Reversible Decoupling Network (RDNet), which employs a reversible encoder to secure valuable information while flexibly decoupling transmission- and reflection-relevant features during the forward pass. Furthermore, we customize a transmission-rate-aware prompt generator to dynamically calibrate features, further boosting performance. Extensive experiments demonstrate the superiority of RDNet over existing SOTA methods on five widely-adopted benchmark datasets. RDNet achieves the best performance in the NTIRE 2025 Single Image Reflection Removal in the Wild Challenge in both fidelity and perceptual comparison. Our code is available at https://github.com/lime-j/RDNet
format Preprint
id arxiv_https___arxiv_org_abs_2410_08063
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reversible Decoupling Network for Single Image Reflection Removal
Zhao, Hao
Li, Mingjia
Hu, Qiming
Guo, Xiaojie
Computer Vision and Pattern Recognition
Recent deep-learning-based approaches to single-image reflection removal have shown promising advances, primarily for two reasons: 1) the utilization of recognition-pretrained features as inputs, and 2) the design of dual-stream interaction networks. However, according to the Information Bottleneck principle, high-level semantic clues tend to be compressed or discarded during layer-by-layer propagation. Additionally, interactions in dual-stream networks follow a fixed pattern across different layers, limiting overall performance. To address these limitations, we propose a novel architecture called Reversible Decoupling Network (RDNet), which employs a reversible encoder to secure valuable information while flexibly decoupling transmission- and reflection-relevant features during the forward pass. Furthermore, we customize a transmission-rate-aware prompt generator to dynamically calibrate features, further boosting performance. Extensive experiments demonstrate the superiority of RDNet over existing SOTA methods on five widely-adopted benchmark datasets. RDNet achieves the best performance in the NTIRE 2025 Single Image Reflection Removal in the Wild Challenge in both fidelity and perceptual comparison. Our code is available at https://github.com/lime-j/RDNet
title Reversible Decoupling Network for Single Image Reflection Removal
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.08063