# Deep Image Compositing

arXiv: https://arxiv.org/abs/2011.02146 · HTML: https://mlsanity.com/paper/2011.02146/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2020.

## Built on by (most cited first, 21 of 21)

- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation](https://mlsanity.com/paper/2403.10701/) (2024)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Relightful Harmonization: Lighting-aware Portrait Background Replacement](https://mlsanity.com/paper/2312.06886/) (2023)
- [ControlCom: Controllable Image Composition using Diffusion Model](https://mlsanity.com/paper/2308.10040/) (2023)
- [Shadow Generation for Composite Image in Real-world Scenes](https://mlsanity.com/paper/2104.10338/) (2021)
- [PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering](https://mlsanity.com/paper/2403.05053/) (2024)
- [DreamCom: Finetuning Text-guided Inpainting Model for Image Composition](https://mlsanity.com/paper/2309.15508/) (2023)
- [Shadow Generation for Composite Image Using Diffusion model](https://mlsanity.com/paper/2403.15234/) (2024)
- [TopNet: Transformer-based Object Placement Network for Image Compositing](https://mlsanity.com/paper/2304.03372/) (2023)
- [3D-aware Blending with Generative NeRFs](https://mlsanity.com/paper/2302.06608/) (2023)
- [Deep Image Matting: A Comprehensive Survey](https://mlsanity.com/paper/2304.04672/) (2023)
- [MVOC: a training-free multiple video object composition method with diffusion models](https://mlsanity.com/paper/2406.15829/) (2024)
- [Edit3K: Universal Representation Learning for Video Editing Components](https://mlsanity.com/paper/2403.16048/) (2024)
- [GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing](https://mlsanity.com/paper/2204.00125/) (2022)
- [BIFR"OST: 3D-Aware Image compositing with Language Instructions](https://mlsanity.com/paper/2410.19079/) (2024)
- [Varying Manifolds in Diffusion: From Time-varying Geometries to Visual Saliency](https://mlsanity.com/paper/2406.18588/) (2024)
- [Geometry-Editable and Appearance-Preserving Object Compositon](https://mlsanity.com/paper/2505.20914/) (2025)
- [PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories](https://mlsanity.com/paper/2602.00267/) (2026)
- [Multi-encoder Network for Parameter Reduction of a Kernel-based Interpolation Architecture](https://mlsanity.com/paper/2205.06723/) (2022)

## Abstract (arXiv)

Image compositing is a task of combining regions from different images to compose a new image. A common use case is background replacement of portrait images. To obtain high quality composites, professionals typically manually perform multiple editing steps such as segmentation, matting and foreground color decontamination, which is very time consuming even with sophisticated photo editing tools. In this paper, we propose a new method which can automatically generate high-quality image compositing without any user input. Our method can be trained end-to-end to optimize exploitation of contextual and color information of both foreground and background images, where the compositing quality is considered in the optimization. Specifically, inspired by Laplacian pyramid blending, a dense-connected multi-stream fusion network is proposed to effectively fuse the information from the foreground and background images at different scales. In addition, we introduce a self-taught strategy to progressively train from easy to complex cases to mitigate the lack of training data. Experiments show that the proposed method can automatically generate high-quality composites and outperforms existing methods both qualitatively and quantitatively.