# Semantic-guided Multi-Mask Image Harmonization

arXiv: https://arxiv.org/abs/2207.11722 · HTML: https://mlsanity.com/paper/2207.11722/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 24 Jul 2022.

## Builds on (most cited first, 17 of 17)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks](https://mlsanity.com/paper/1710.01992/) (2017)
- [DoveNet: Deep Image Harmonization via Domain Verification](https://mlsanity.com/paper/1911.13239/) (2019)
- [Deep Image Harmonization](https://mlsanity.com/paper/1703.00069/) (2017)
- [Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing](https://mlsanity.com/paper/1703.05446/) (2017)
- [Improving the Harmony of the Composite Image by Spatial-Separated Attention Module](https://mlsanity.com/paper/1907.06406/) (2019)
- [Region-aware Adaptive Instance Normalization for Image Harmonization](https://mlsanity.com/paper/2106.02853/) (2021)
- [Learning a Discriminative Model for the Perception of Realism in Composite Images](https://mlsanity.com/paper/1510.00477/) (2015)
- [BargainNet: Background-Guided Domain Translation for Image Harmonization](https://mlsanity.com/paper/2009.09169/) (2020)
- [Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network](https://mlsanity.com/paper/2012.15020/) (2020)
- [Deep Preset: Blending and Retouching Photos with Color Style Transfer](https://mlsanity.com/paper/2007.10701/) (2020)
- [Inharmonious Region Localization](https://mlsanity.com/paper/2104.09453/) (2021)

## Built on by (most cited first, 6 of 6)

- [ControlCom: Controllable Image Composition using Diffusion Model](https://mlsanity.com/paper/2308.10040/) (2023)
- [DreamCom: Finetuning Text-guided Inpainting Model for Image Composition](https://mlsanity.com/paper/2309.15508/) (2023)
- [Deep Image Harmonization in Dual Color Spaces](https://mlsanity.com/paper/2308.02813/) (2023)
- [Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation](https://mlsanity.com/paper/2308.00356/) (2023)
- [Point Cloud Self-supervised Learning via 3D to Multi-view Masked Learner](https://mlsanity.com/paper/2311.10887/) (2023)
- [Diverse Image Harmonization](https://mlsanity.com/paper/2407.15481/) (2024)

## Abstract (arXiv)

Previous harmonization methods focus on adjusting one inharmonious region in an image based on an input mask. They may face problems when dealing with different perturbations on different semantic regions without available input masks. To deal with the problem that one image has been pasted with several foregrounds coming from different images and needs to harmonize them towards different domain directions without any mask as input, we propose a new semantic-guided multi-mask image harmonization task. Different from the previous single-mask image harmonization task, each inharmonious image is perturbed with different methods according to the semantic segmentation masks. Two challenging benchmarks, HScene and HLIP, are constructed based on 150 and 19 semantic classes, respectively. Furthermore, previous baselines focus on regressing the exact value for each pixel of the harmonized images. The generated results are in the `black box' and cannot be edited. In this work, we propose a novel way to edit the inharmonious images by predicting a series of operator masks. The masks indicate the level and the position to apply a certain image editing operation, which could be the brightness, the saturation, and the color in a specific dimension. The operator masks provide more flexibility for users to edit the image further. Extensive experiments verify that the operator mask-based network can further improve those state-of-the-art methods which directly regress RGB images when the perturbations are structural. Experiments have been conducted on our constructed benchmarks to verify that our proposed operator mask-based framework can locate and modify the inharmonious regions in more complex scenes. Our code and models are available at https://github.com/XuqianRen/Semantic-guided-Multi-mask-Image-Harmonization.git.