# One-shot Detail Retouching with Patch Space Neural Transformation Blending

arXiv: https://arxiv.org/abs/2210.01217 · HTML: https://mlsanity.com/paper/2210.01217/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 61 references that are in the map.
- First posted on arXiv 3 Oct 2022.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Visual Attribute Transfer through Deep Image Analogy](https://mlsanity.com/paper/1705.01088/) (2017)
- [DeepLPF: Deep Local Parametric Filters for Image Enhancement](https://mlsanity.com/paper/2003.13985/) (2020)
- [LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond](https://mlsanity.com/paper/2105.10422/) (2021)
- [Conditional Sequential Modulation for Efficient Global Image Retouching](https://mlsanity.com/paper/2009.10390/) (2020)
- [Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning](https://mlsanity.com/paper/1804.04450/) (2018)
- [Spatially-Adaptive Pixelwise Networks for Fast Image Translation](https://mlsanity.com/paper/2012.02992/) (2020)
- [Fast Image Processing with Fully-Convolutional Networks](https://mlsanity.com/paper/1709.00643/) (2017)
- [ReconfigISP: Reconfigurable Camera Image Processing Pipeline](https://mlsanity.com/paper/2109.04760/) (2021)
- [Exposure: A White-Box Photo Post-Processing Framework](https://mlsanity.com/paper/1709.09602/) (2017)
- [TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images](https://mlsanity.com/paper/2004.04634/) (2020)
- [MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2105.14110/) (2021)
- [Makeup like a superstar: Deep Localized Makeup Transfer Network](https://mlsanity.com/paper/1604.07102/) (2016)
- [Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping](https://mlsanity.com/paper/2209.15165/) (2022)
- [Multimodal Prediction and Personalization of Photo Edits with Deep Generative Models](https://mlsanity.com/paper/1704.04997/) (2017)
- [Automatic Photo Adjustment Using Deep Neural Networks](https://mlsanity.com/paper/1412.7725/) (2014)
- [Deep Semantics-Aware Photo Adjustment](https://mlsanity.com/paper/1706.08260/) (2017)
- [Automatic Image Stylization Using Deep Fully Convolutional Networks](https://mlsanity.com/paper/1811.10872/) (2018)

## Abstract (arXiv)

Photo retouching is a difficult task for novice users as it requires expert knowledge and advanced tools. Photographers often spend a great deal of time generating high-quality retouched photos with intricate details. In this paper, we introduce a one-shot learning based technique to automatically retouch details of an input image based on just a single pair of before and after example images. Our approach provides accurate and generalizable detail edit transfer to new images. We achieve these by proposing a new representation for image to image maps. Specifically, we propose neural field based transformation blending in the patch space for defining patch to patch transformations for each frequency band. This parametrization of the map with anchor transformations and associated weights, and spatio-spectral localized patches, allows us to capture details well while staying generalizable. We evaluate our technique both on known ground truth filters and artist retouching edits. Our method accurately transfers complex detail retouching edits.