# Robust Reflection Removal with Reflection-free Flash-only Cues

arXiv: https://arxiv.org/abs/2103.04273 · HTML: https://mlsanity.com/paper/2103.04273/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 47 references that are in the map.
- First posted on arXiv 7 Mar 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [Blind Video Temporal Consistency via Deep Video Prior](https://mlsanity.com/paper/2010.11838/) (2020)
- [Polarized Reflection Removal with Perfect Alignment in the Wild](https://mlsanity.com/paper/2003.12789/) (2020)
- [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)
- [Self-calibrating Deep Photometric Stereo Networks](https://mlsanity.com/paper/1903.07366/) (2019)
- [Learning to See Through Obstructions](https://mlsanity.com/paper/2004.01180/) (2020)
- [Separating Reflection and Transmission Images in the Wild](https://mlsanity.com/paper/1712.02099/) (2017)
- [Fast Single Image Reflection Suppression via Convex Optimization](https://mlsanity.com/paper/1903.03889/) (2019)

## Built on by (most cited first, 30 of 34)

- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Single Image Reflection Separation via Component Synergy](https://mlsanity.com/paper/2308.10027/) (2023)
- [Revisiting Single Image Reflection Removal In the Wild](https://mlsanity.com/paper/2311.17320/) (2023)
- [Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery](https://mlsanity.com/paper/2308.16460/) (2023)
- [Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections](https://mlsanity.com/paper/2304.08706/) (2023)
- [Deep Video Prior for Video Consistency and Propagation](https://mlsanity.com/paper/2201.11632/) (2022)
- [PolarFree: Polarization-based Reflection-free Imaging](https://mlsanity.com/paper/2503.18055/) (2025)
- [Neural Spline Fields for Burst Image Fusion and Layer Separation](https://mlsanity.com/paper/2312.14235/) (2023)
- [Language-guided Image Reflection Separation](https://mlsanity.com/paper/2402.11874/) (2024)
- [DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos](https://mlsanity.com/paper/2405.17705/) (2024)
- [Image Demoireing in RAW and sRGB Domains](https://mlsanity.com/paper/2312.09063/) (2023)
- [Robust Reflection Removal with Flash-only Cues in the Wild](https://mlsanity.com/paper/2211.02914/) (2022)
- [A Categorized Reflection Removal Dataset with Diverse Real-world Scenes](https://mlsanity.com/paper/2108.03380/) (2021)
- [Neural Camera Simulators](https://mlsanity.com/paper/2104.05237/) (2021)
- [Removing Reflections from RAW Photos](https://mlsanity.com/paper/2404.14414/) (2024)
- [Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation](https://mlsanity.com/paper/2501.00637/) (2024)
- [UniSER: A Foundation Model for Unified Soft Effects Removal](https://mlsanity.com/paper/2511.14183/) (2025)
- [Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separation](https://mlsanity.com/paper/2601.00322/) (2026)
- [FIRM: Flexible Interactive Reflection reMoval](https://mlsanity.com/paper/2406.01555/) (2024)
- [Adaptive Network Combination for Single-Image Reflection Removal: A Domain Generalization Perspective](https://mlsanity.com/paper/2204.01505/) (2022)
- [Benchmarking Ultra-High-Definition Image Reflection Removal](https://mlsanity.com/paper/2308.00265/) (2023)
- [Alignment-free Raw Video Demoireing](https://mlsanity.com/paper/2408.10679/) (2024)
- [Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats](https://mlsanity.com/paper/2410.02764/) (2024)
- [Single-image reflection removal via self-supervised diffusion models](https://mlsanity.com/paper/2412.20466/) (2024)
- [GFRRN: Explore the Gaps in Single Image Reflection Removal](https://mlsanity.com/paper/2602.22695/) (2026)
- [Seeing Far in the Dark with Patterned Flash](https://mlsanity.com/paper/2207.12570/) (2022)
- [ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation](https://mlsanity.com/paper/2601.17468/) (2026)
- [FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal](https://mlsanity.com/paper/2603.19036/) (2026)
- [M2-Net: Multi-stages Specular Highlight Detection and Removal in Multi-scenes](https://mlsanity.com/paper/2207.09965/) (2022)
- [Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagery](https://mlsanity.com/paper/2511.16887/) (2025)

## Abstract (arXiv)

We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambient image from the corresponding flash image in raw data space. The flash-only image is equivalent to an image taken in a dark environment with only a flash on. We observe that this flash-only image is visually reflection-free, and thus it can provide robust cues to infer the reflection in the ambient image. Since the flash-only image usually has artifacts, we further propose a dedicated model that not only utilizes the reflection-free cue but also avoids introducing artifacts, which helps accurately estimate reflection and transmission. Our experiments on real-world images with various types of reflection demonstrate the effectiveness of our model with reflection-free flash-only cues: our model outperforms state-of-the-art reflection removal approaches by more than 5.23dB in PSNR, 0.04 in SSIM, and 0.068 in LPIPS. Our source code and dataset are publicly available at {github.com/ChenyangLEI/flash-reflection-removal}.