mlsanityData to 7 Oct 2026

One-shot Detail Retouching with Patch Space Neural Transformation Blending

arXiv 2210.01217 ↗First posted 3 Oct 2022cs.CV cs.GRcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 61 references that are in the map. First posted on arXiv 3 Oct 2022.

Builds on

22 of 61 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  4. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  5. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  6. 2017Visual Attribute Transfer through Deep Image Analogycited by 123
  7. 2020DeepLPF: Deep Local Parametric Filters for Image Enhancementcited by 107
  8. 2021LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyondcited by 88
  9. 2020Conditional Sequential Modulation for Efficient Global Image Retouchingcited by 71
  10. 2018Distort-and-Recover: Color Enhancement using Deep Reinforcement Learningcited by 52
  11. 2020Spatially-Adaptive Pixelwise Networks for Fast Image Translationcited by 45
  12. 2017Fast Image Processing with Fully-Convolutional Networkscited by 41
10 more
  1. 2021ReconfigISP: Reconfigurable Camera Image Processing Pipelinecited by 30
  2. 2017Exposure: A White-Box Photo Post-Processing Frameworkcited by 27
  3. 2020TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Imagescited by 23
  4. 2021MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translationcited by 10
  5. 2016Makeup like a superstar: Deep Localized Makeup Transfer Networkcited by 7
  6. 2022Distilling Style from Image Pairs for Global Forward and Inverse Tone Mappingcited by 5
  7. 2017Multimodal Prediction and Personalization of Photo Edits with Deep Generative Modelscited by 2
  8. 2014Automatic Photo Adjustment Using Deep Neural Networkscited by 1
  9. 2017Deep Semantics-Aware Photo Adjustmentcited by 1
  10. 2018Automatic Image Stylization Using Deep Fully Convolutional Networkscited by 1

Built on by

Not cited yet.