# Foreground-aware Semantic Representations for Image Harmonization

arXiv: https://arxiv.org/abs/2006.00809 · HTML: https://mlsanity.com/paper/2006.00809/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2020.

## Built on by (most cited first, 30 of 53)

- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Harmonizer: Learning to Perform White-Box Image and Video Harmonization](https://mlsanity.com/paper/2207.01322/) (2022)
- [High-Resolution Image Harmonization via Collaborative Dual Transformations](https://mlsanity.com/paper/2109.06671/) (2021)
- [DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization](https://mlsanity.com/paper/2207.04788/) (2022)
- [ControlCom: Controllable Image Composition using Diffusion Model](https://mlsanity.com/paper/2308.10040/) (2023)
- [Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization](https://mlsanity.com/paper/2109.05750/) (2021)
- [SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization](https://mlsanity.com/paper/2204.13962/) (2022)
- [Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model](https://mlsanity.com/paper/2306.07596/) (2023)
- [Dense Pixel-to-Pixel Harmonization via Continuous Image Representation](https://mlsanity.com/paper/2303.01681/) (2023)
- [Learning Interactive Driving Policies via Data-driven Simulation](https://mlsanity.com/paper/2111.12137/) (2021)
- [DreamCom: Finetuning Text-guided Inpainting Model for Image Composition](https://mlsanity.com/paper/2309.15508/) (2023)
- [FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior](https://mlsanity.com/paper/2407.04947/) (2024)
- [PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing](https://mlsanity.com/paper/2303.00137/) (2023)
- [DeCo: Decoupled Human-Centered Diffusion Video Editing with Motion Consistency](https://mlsanity.com/paper/2408.07481/) (2024)
- [Fast Object Placement Assessment](https://mlsanity.com/paper/2205.14280/) (2022)
- [Hierarchical Dynamic Image Harmonization](https://mlsanity.com/paper/2211.08639/) (2022)
- [LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization](https://mlsanity.com/paper/2304.13166/) (2023)
- [Deep Image Harmonization in Dual Color Spaces](https://mlsanity.com/paper/2308.02813/) (2023)
- [Deep Image Harmonization by Bridging the Reality Gap](https://mlsanity.com/paper/2103.17104/) (2021)
- [Painterly Image Harmonization in Dual Domains](https://mlsanity.com/paper/2212.08846/) (2022)
- [Deep Video Harmonization with Color Mapping Consistency](https://mlsanity.com/paper/2205.00687/) (2022)
- [FRIH: Fine-grained Region-aware Image Harmonization](https://mlsanity.com/paper/2205.06448/) (2022)
- [Zero-Shot Image Harmonization with Generative Model Prior](https://mlsanity.com/paper/2307.08182/) (2023)
- [MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation](https://mlsanity.com/paper/2505.21483/) (2025)
- [Image Harmonization by Matching Regional References](https://mlsanity.com/paper/2204.04715/) (2022)
- [Deep Image Harmonization with Learnable Augmentation](https://mlsanity.com/paper/2308.00376/) (2023)
- [Learning Global-aware Kernel for Image Harmonization](https://mlsanity.com/paper/2305.11676/) (2023)
- [Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation](https://mlsanity.com/paper/2308.00356/) (2023)
- [Privacy-Preserving Synthetic Continual Semantic Segmentation for Robotic Surgery](https://mlsanity.com/paper/2402.05860/) (2024)
- [MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues](https://mlsanity.com/paper/2512.03046/) (2025)

## Abstract (arXiv)

Image harmonization is an important step in photo editing to achieve visual consistency in composite images by adjusting the appearances of foreground to make it compatible with background. Previous approaches to harmonize composites are based on training of encoder-decoder networks from scratch, which makes it challenging for a neural network to learn a high-level representation of objects. We propose a novel architecture to utilize the space of high-level features learned by a pre-trained classification network. We create our models as a combination of existing encoder-decoder architectures and a pre-trained foreground-aware deep high-resolution network. We extensively evaluate the proposed method on existing image harmonization benchmark and set up a new state-of-the-art in terms of MSE and PSNR metrics. The code and trained models are available at urlhttps://github.com/saic-vul/imageharmonization.