# Single-image reflection removal via self-supervised diffusion models

arXiv: https://arxiv.org/abs/2412.20466 · HTML: https://mlsanity.com/paper/2412.20466/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 29 Dec 2024.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Feedback Network for Image Super-Resolution](https://mlsanity.com/paper/1903.09814/) (2019)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing](https://mlsanity.com/paper/1708.03474/) (2017)
- [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)
- [Single Image Reflection Separation via Component Synergy](https://mlsanity.com/paper/2308.10027/) (2023)
- [Robust Reflection Removal with Reflection-free Flash-only Cues](https://mlsanity.com/paper/2103.04273/) (2021)
- [CRRN: Multi-Scale Guided Concurrent Reflection Removal Network](https://mlsanity.com/paper/1805.11802/) (2018)
- [Separating Reflection and Transmission Images in the Wild](https://mlsanity.com/paper/1712.02099/) (2017)
- [Improving Misaligned Multi-modality Image Fusion with One-stage Progressive Dense Registration](https://mlsanity.com/paper/2308.11165/) (2023)
- [Single Image Super Resolution based on a Modified U-net with Mixed Gradient Loss](https://mlsanity.com/paper/1911.09428/) (2019)
- [Joint Self-supervised Depth and Optical Flow Estimation towards Dynamic Objects](https://mlsanity.com/paper/2310.00011/) (2023)
- [Self-supervised Monocular Depth Estimation on Water Scenes via Specular Reflection Prior](https://mlsanity.com/paper/2404.07176/) (2024)

## Built on by (most cited first, 2 of 2)

- [Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation](https://mlsanity.com/paper/2509.05746/) (2025)
- [CLIP-aware Domain-Adaptive Super-Resolution](https://mlsanity.com/paper/2505.12391/) (2025)

## Abstract (arXiv)

Reflections often degrade the visual quality of images captured through transparent surfaces, and reflection removal methods suffers from the shortage of paired real-world samples.This paper proposes a hybrid approach that combines cycle-consistency with denoising diffusion probabilistic models (DDPM) to effectively remove reflections from single images without requiring paired training data. The method introduces a Reflective Removal Network (RRN) that leverages DDPMs to model the decomposition process and recover the transmission image, and a Reflective Synthesis Network (RSN) that re-synthesizes the input image using the separated components through a nonlinear attention-based mechanism. Experimental results demonstrate the effectiveness of the proposed method on the SIR2, Flash-Based Reflection Removal (FRR) Dataset, and a newly introduced Museum Reflection Removal (MRR) dataset, showing superior performance compared to state-of-the-art methods.