# Principled Reflection Separation via Nonlinear Superposition and Feature Interaction

arXiv: https://arxiv.org/abs/2606.02831 · HTML: https://mlsanity.com/paper/2606.02831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 94 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 30 of 36)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [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)
- [Location-aware Single Image Reflection Removal](https://mlsanity.com/paper/2012.07131/) (2020)
- [Learning to See Through Obstructions](https://mlsanity.com/paper/2004.01180/) (2020)
- [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)
- [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)
- [CRRN: Multi-Scale Guided Concurrent Reflection Removal Network](https://mlsanity.com/paper/1805.11802/) (2018)
- [The Visual Centrifuge: Model-Free Layered Video Representations](https://mlsanity.com/paper/1812.01461/) (2018)
- [Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance](https://mlsanity.com/paper/2012.00945/) (2020)
- [Reversible Decoupling Network for Single Image Reflection Removal](https://mlsanity.com/paper/2410.08063/) (2024)
- [Learning to See Through Obstructions with Layered Decomposition](https://mlsanity.com/paper/2008.04902/) (2020)
- [Separating Reflection and Transmission Images in the Wild](https://mlsanity.com/paper/1712.02099/) (2017)
- [Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections](https://mlsanity.com/paper/2304.08706/) (2023)
- [PolarFree: Polarization-based Reflection-free Imaging](https://mlsanity.com/paper/2503.18055/) (2025)
- [Language-guided Image Reflection Separation](https://mlsanity.com/paper/2402.11874/) (2024)
- [Deep-Masking Generative Network: A Unified Framework for Background Restoration from Superimposed Images](https://mlsanity.com/paper/2010.04324/) (2020)

## Abstract (arXiv)

Single-image reflection separation is fundamentally challenged by the entanglement of transmission and reflection layers under complex image formation processes. Existing approaches largely rely on simplified assumptions or independent modeling, limiting their ability to handle real-world scenarios. In this work, we revisit the problem from a unified perspective and identify a key issue of existing approaches, i.e., the widely adopted linear composition model in the sRGB domain fails to capture the nonlinear coupling introduced by real-world image signal processing pipelines. To address this, we introduce a learnable nonlinear superposition model that more faithfully characterizes layer interactions and improves decomposition fidelity. Building upon this formulation, we propose a generalized dual-stream interactive framework that explicitly models bidirectional dependencies between transmission and reflection through feature exchange. This framework unifies activation-, gating-, and attention-based interaction mechanisms, and is compatible with both CNN and Transformer backbones. Extensive experiments on diverse real-world benchmarks demonstrate that the proposed approach achieves superior performance with strong generalization capability. More importantly, our study reveals that reflection separation is not about undoing a linear mixture, but about learning nonlinear formation and interaction}, offering new insights into the design of principled image decomposition models. Code and models are publicly available at https://mingcv.github.io/DIRS-Page.