# Reversible Decoupling Network for Single Image Reflection Removal

arXiv: https://arxiv.org/abs/2410.08063 · HTML: https://mlsanity.com/paper/2410.08063/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 55 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 30 of 33)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [The Reversible Residual Network: Backpropagation Without Storing Activations](https://mlsanity.com/paper/1707.04585/) (2017)
- [Focal Modulation Networks](https://mlsanity.com/paper/2203.11926/) (2022)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Hypercolumns for Object Segmentation and Fine-grained Localization](https://mlsanity.com/paper/1411.5752/) (2014)
- [How to represent part-whole hierarchies in a neural network](https://mlsanity.com/paper/2102.12627/) (2021)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [Single Image Reflection Removal through Cascaded Refinement](https://mlsanity.com/paper/1911.06634/) (2019)
- [Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements](https://mlsanity.com/paper/1904.00637/) (2019)
- [Location-aware Single Image Reflection Removal](https://mlsanity.com/paper/2012.07131/) (2020)
- [Single Image Reflection Separation via Component Synergy](https://mlsanity.com/paper/2308.10027/) (2023)
- [WINNet: Wavelet-inspired Invertible Network for Image Denoising](https://mlsanity.com/paper/2109.06381/) (2021)
- [Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution](https://mlsanity.com/paper/2303.05156/) (2023)
- [Learning Depth Estimation for Transparent and Mirror Surfaces](https://mlsanity.com/paper/2307.15052/) (2023)
- [Revisiting Single Image Reflection Removal In the Wild](https://mlsanity.com/paper/2311.17320/) (2023)
- [Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation](https://mlsanity.com/paper/2110.10546/) (2021)
- [Reversible Column Networks](https://mlsanity.com/paper/2212.11696/) (2022)
- [CRRN: Multi-Scale Guided Concurrent Reflection Removal Network](https://mlsanity.com/paper/1805.11802/) (2018)
- [Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance](https://mlsanity.com/paper/2012.00945/) (2020)
- [Language-guided Image Reflection Separation](https://mlsanity.com/paper/2402.11874/) (2024)

## Built on by (most cited first, 22 of 22)

- [Dereflection Any Image with Diffusion Priors and Diversified Data](https://mlsanity.com/paper/2503.17347/) (2025)
- [RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models](https://mlsanity.com/paper/2603.25502/) (2026)
- [Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separation](https://mlsanity.com/paper/2601.00322/) (2026)
- [Reflection Removal through Efficient Adaptation of Diffusion Transformers](https://mlsanity.com/paper/2512.05000/) (2025)
- [Rectifying Latent Space for Generative Single-Image Reflection Removal](https://mlsanity.com/paper/2512.06358/) (2025)
- [Degradation-Aware Image Enhancement via Vision-Language Classification](https://mlsanity.com/paper/2506.05450/) (2025)
- [GFRRN: Explore the Gaps in Single Image Reflection Removal](https://mlsanity.com/paper/2602.22695/) (2026)
- [Single Image Reflection Separation via Dual Prior Interaction Transformer](https://mlsanity.com/paper/2505.12641/) (2025)
- [OpenRR-5k: A Large-Scale Benchmark for Reflection Removal in the Wild](https://mlsanity.com/paper/2506.05482/) (2025)
- [ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation](https://mlsanity.com/paper/2601.17468/) (2026)
- [Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline](https://mlsanity.com/paper/2603.16446/) (2026)
- [FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal](https://mlsanity.com/paper/2603.19036/) (2026)
- [On the Global Photometric Alignment for Low-Level Vision](https://mlsanity.com/paper/2604.08172/) (2026)
- [EvReflection: Event-Driven Micro-Dynamics for Reflection Removal](https://mlsanity.com/paper/2608.06184/) (2026)
- [SIRR-LMM: Single-image Reflection Removal via Large Multimodal Model](https://mlsanity.com/paper/2601.07209/) (2026)
- [Representative Attention For Vision Transformers](https://mlsanity.com/paper/2605.14913/) (2026)
- [Principled Reflection Separation via Nonlinear Superposition and Feature Interaction](https://mlsanity.com/paper/2606.02831/) (2026)
- [Reflection Separation from a Single Image via Joint Latent Diffusion](https://mlsanity.com/paper/2606.04107/) (2026)
- [PRISM: Latent Composition Consistency for Single-Image Reflection Removal](https://mlsanity.com/paper/2606.31513/) (2026)
- [ReLo-IRR: Reflection-Guided LoRA Framework for Image Reflection Removal](https://mlsanity.com/paper/2607.02957/) (2026)
- [LowAux-RDNet: Low-Pass Residual Supervision with Scene-Balanced Real-World Training for Single-Image Reflection Removal](https://mlsanity.com/paper/2607.22707/) (2026)
- [LoViF 2026 The First Challenge on Unified Removal of Raindrops and Reflections: Methods and Results](https://mlsanity.com/paper/2608.22723/) (2026)

## Abstract (arXiv)

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