# Retinex-guided Channel-grouping based Patch Swap for Arbitrary Style Transfer

arXiv: https://arxiv.org/abs/2309.10528 · HTML: https://mlsanity.com/paper/2309.10528/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 19 Sep 2023.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis](https://mlsanity.com/paper/1701.02096/) (2017)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Arbitrary Style Transfer with Style-Attentional Networks](https://mlsanity.com/paper/1812.02342/) (2018)
- [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2108.03647/) (2021)
- [Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration](https://mlsanity.com/paper/1805.03857/) (2018)
- [Fast Patch-based Style Transfer of Arbitrary Style](https://mlsanity.com/paper/1612.04337/) (2016)
- [Exploring the structure of a real-time, arbitrary neural artistic stylization network](https://mlsanity.com/paper/1705.06830/) (2017)
- [Dynamic Instance Normalization for Arbitrary Style Transfer](https://mlsanity.com/paper/1911.06953/) (2019)
- [Arbitrary Style Transfer via Multi-Adaptation Network](https://mlsanity.com/paper/2005.13219/) (2020)
- [Attention-aware Multi-stroke Style Transfer](https://mlsanity.com/paper/1901.05127/) (2019)
- [MSR-net:Low-light Image Enhancement Using Deep Convolutional Network](https://mlsanity.com/paper/1711.02488/) (2017)
- [Manifold Alignment for Semantically Aligned Style Transfer](https://mlsanity.com/paper/2005.10777/) (2020)
- [Style-Aware Normalized Loss for Improving Arbitrary Style Transfer](https://mlsanity.com/paper/2104.10064/) (2021)
- [Learning Graph Neural Networks for Image Style Transfer](https://mlsanity.com/paper/2207.11681/) (2022)
- [DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer](https://mlsanity.com/paper/2101.06381/) (2021)
- [Non-Local Representation based Mutual Affine-Transfer Network for Photorealistic Stylization](https://mlsanity.com/paper/1907.10274/) (2019)

## Abstract (arXiv)

The basic principle of the patch-matching based style transfer is to substitute the patches of the content image feature maps by the closest patches from the style image feature maps. Since the finite features harvested from one single aesthetic style image are inadequate to represent the rich textures of the content natural image, existing techniques treat the full-channel style feature patches as simple signal tensors and create new style feature patches via signal-level fusion, which ignore the implicit diversities existed in style features and thus fail for generating better stylised results. In this paper, we propose a Retinex theory guided, channel-grouping based patch swap technique to solve the above challenges. Channel-grouping strategy groups the style feature maps into surface and texture channels, which prevents the winner-takes-all problem. Retinex theory based decomposition controls a more stable channel code rate generation. In addition, we provide complementary fusion and multi-scale generation strategy to prevent unexpected black area and over-stylised results respectively. Experimental results demonstrate that the proposed method outperforms the existing techniques in providing more style-consistent textures while keeping the content fidelity.