Inharmonious Region Localization by Magnifying Domain Discrepancy
Not on the map. Why?
Abstract (arXiv)
Inharmonious region localization aims to localize the region in a synthetic image which is incompatible with surrounding background. The inharmony issue is mainly attributed to the color and illumination inconsistency produced by image editing techniques. In this work, we tend to transform the input image to another color space to magnify the domain discrepancy between inharmonious region and background, so that the model can identify the inharmonious region more easily. To this end, we present a novel framework consisting of a color mapping module and an inharmonious region localization network, in which the former is equipped with a novel domain discrepancy magnification loss and the latter could be an arbitrary localization network. Extensive experiments on image harmonization dataset show the superiority of our designed framework. Our code is available at https://github.com/bcmi/MadisNet-Inharmonious-Region-Localization.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 30 of its 49 references that are in the map. First posted on arXiv 30 Sep 2022.
Builds on
30 of 49 references.
References · 30
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
- 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
- 2018Self-Attention Generative Adversarial Networkscited by 809
- 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
- 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
- 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
- 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
- 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
18 more
- 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
- 2020Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-timecited by 163
- 2018Fighting Fake News: Image Splice Detection via Learned Self-Consistencycited by 136
- 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 134
- 2020Suppress and Balance: A Simple Gated Network for Salient Object Detectioncited by 126
- 2017Deep Image Harmonizationcited by 120
- 2020SPAN: Spatial Pyramid Attention Network forImage Manipulation Localizationcited by 92
- 2019Improving the Harmony of the Composite Image by Spatial-Separated Attention Modulecited by 73
- 2021Region-aware Adaptive Instance Normalization for Image Harmonizationcited by 71
- 2017Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)cited by 64
- 2019Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeriescited by 59
- 2020Foreground-aware Semantic Representations for Image Harmonizationcited by 53
- 2020BargainNet: Background-Guided Domain Translation for Image Harmonizationcited by 52
- 2021TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformationscited by 48
- 2018Generate, Segment and Refine: Towards Generic Manipulation Segmentationcited by 33
- 2020Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfercited by 31
- 2019Constrained R-CNN: A general image manipulation detection modelcited by 29
- 2021Inharmonious Region Localizationcited by 5
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.
- 2023Deep Image Harmonization in Dual Color Spacescited by 12
- 2022Inharmonious Region Localization with Auxiliary Style Featurecited by 1
- 2023Deep Image Harmonization in Dual Color Spaces5 Aug 2023
- 2022Inharmonious Region Localization with Auxiliary Style Feature5 Oct 2022