# Adaptive Network Combination for Single-Image Reflection Removal: A Domain Generalization Perspective

arXiv: https://arxiv.org/abs/2204.01505 · HTML: https://mlsanity.com/paper/2204.01505/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 59 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Domain Adaptive Ensemble Learning](https://mlsanity.com/paper/2003.07325/) (2020)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [Best sources forward: domain generalization through source-specific nets](https://mlsanity.com/paper/1806.05810/) (2018)
- [DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets](https://mlsanity.com/paper/2010.06208/) (2020)
- [Polarized Reflection Removal with Perfect Alignment in the Wild](https://mlsanity.com/paper/2003.12789/) (2020)
- [Domain Generalization with Domain-Specific Aggregation Modules](https://mlsanity.com/paper/1809.10966/) (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)
- [Deep Network Interpolation for Continuous Imagery Effect Transition](https://mlsanity.com/paper/1811.10515/) (2018)
- [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)
- [Robust Reflection Removal with Reflection-free Flash-only Cues](https://mlsanity.com/paper/2103.04273/) (2021)
- [Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation](https://mlsanity.com/paper/2110.10546/) (2021)
- [Checkpoint Ensembles: Ensemble Methods from a Single Training Process](https://mlsanity.com/paper/1710.03282/) (2017)
- [Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance](https://mlsanity.com/paper/2012.00945/) (2020)
- [Separating Reflection and Transmission Images in the Wild](https://mlsanity.com/paper/1712.02099/) (2017)
- [Deep-Masking Generative Network: A Unified Framework for Background Restoration from Superimposed Images](https://mlsanity.com/paper/2010.04324/) (2020)
- [A Categorized Reflection Removal Dataset with Diverse Real-world Scenes](https://mlsanity.com/paper/2108.03380/) (2021)
- [Robust Optical Flow Estimation of Double-Layer Images under Transparency or Reflection](https://mlsanity.com/paper/1605.01825/) (2016)
- [Dynamic-Net: Tuning the Objective Without Re-training for Synthesis Tasks](https://mlsanity.com/paper/1811.08760/) (2018)

## Built on by (most cited first, 3 of 3)

- [Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections](https://mlsanity.com/paper/2304.08706/) (2023)
- [Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective](https://mlsanity.com/paper/2312.15408/) (2023)
- [Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution](https://mlsanity.com/paper/2607.15711/) (2026)

## Abstract (arXiv)

Recently, multiple synthetic and real-world datasets have been built to facilitate the training of deep single image reflection removal (SIRR) models. Meanwhile, diverse testing sets are also provided with different types of reflection and scenes. However, the non-negligible domain gaps between training and testing sets make it difficult to learn deep models generalizing well to testing images. The diversity of reflections and scenes further makes it a mission impossible to learn a single model being effective to all testing sets and real-world reflections. In this paper, we tackle these issues by learning SIRR models from a domain generalization perspective. Particularly, for each source set, a specific SIRR model is trained to serve as a domain expert of relevant reflection types. For a given reflection-contaminated image, we present a reflection type-aware weighting (RTAW) module to predict expert-wise weights. RTAW can then be incorporated with adaptive network combination (AdaNEC) for handling different reflection types and scenes, i.e., generalizing to unknown domains. Two representative AdaNEC methods, i.e., output fusion (OF) and network interpolation (NI), are provided by considering both adaptation levels and efficiency. For images from one source set, we train RTAW to only predict expert-wise weights of other domain experts for improving generalization ability, while the weights of all experts are predicted and employed during testing. An in-domain expert (IDE) loss is presented for training RTAW. Extensive experiments show the appealing performance gain of our AdaNEC on different state-of-the-art SIRR networks. Source code and pre-trained models will available at https://github.com/csmliu/AdaNEC.