# Deep Image Blending

arXiv: https://arxiv.org/abs/1910.11495 · HTML: https://mlsanity.com/paper/1910.11495/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2019.

## Built on by (most cited first, 30 of 62)

- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [ARF: Artistic Radiance Fields](https://mlsanity.com/paper/2206.06360/) (2022)
- [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)
- [CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model](https://mlsanity.com/paper/2311.18405/) (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)
- [Towards Unified Deep Image Deraining: A Survey and A New Benchmark](https://mlsanity.com/paper/2310.03535/) (2023)
- [Does FLUX Already Know How to Perform Physically Plausible Image Composition?](https://mlsanity.com/paper/2509.21278/) (2025)
- [Tuning-Free Image Customization with Image and Text Guidance](https://mlsanity.com/paper/2403.12658/) (2024)
- [Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model](https://mlsanity.com/paper/2306.07596/) (2023)
- [IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models](https://mlsanity.com/paper/2311.06792/) (2023)
- [Learning Object Placement via Dual-path Graph Completion](https://mlsanity.com/paper/2207.11464/) (2022)
- [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)
- [Geometry Transfer for Stylizing Radiance Fields](https://mlsanity.com/paper/2402.00863/) (2024)
- [3D-aware Blending with Generative NeRFs](https://mlsanity.com/paper/2302.06608/) (2023)
- [Cross-domain Compositing with Pretrained Diffusion Models](https://mlsanity.com/paper/2302.10167/) (2023)
- [MixerMDM: Learnable Composition of Human Motion Diffusion Models](https://mlsanity.com/paper/2504.01019/) (2025)
- [Painterly Image Harmonization using Diffusion Model](https://mlsanity.com/paper/2308.02228/) (2023)
- [AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment](https://mlsanity.com/paper/2111.07640/) (2021)
- [Painterly Image Harmonization in Dual Domains](https://mlsanity.com/paper/2212.08846/) (2022)
- [Location-Free Camouflage Generation Network](https://mlsanity.com/paper/2203.09845/) (2022)
- [TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided Optimization](https://mlsanity.com/paper/2408.03637/) (2024)
- [Defocus to focus: Photo-realistic bokeh rendering by fusing defocus and radiance priors](https://mlsanity.com/paper/2306.04506/) (2023)
- [FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model](https://mlsanity.com/paper/2311.14926/) (2023)
- [Repositioning the Subject within Image](https://mlsanity.com/paper/2401.16861/) (2024)
- [Edit One for All: Interactive Batch Image Editing](https://mlsanity.com/paper/2401.10219/) (2024)
- [DermSynth3D: Synthesis of in-the-wild Annotated Dermatology Images](https://mlsanity.com/paper/2305.12621/) (2023)

## Abstract (arXiv)

Image composition is an important operation to create visual content. Among image composition tasks, image blending aims to seamlessly blend an object from a source image onto a target image with lightly mask adjustment. A popular approach is Poisson image blending, which enforces the gradient domain smoothness in the composite image. However, this approach only considers the boundary pixels of target image, and thus can not adapt to texture of target image. In addition, the colors of the target image often seep through the original source object too much causing a significant loss of content of the source object. We propose a Poisson blending loss that achieves the same purpose of Poisson image blending. In addition, we jointly optimize the proposed Poisson blending loss as well as the style and content loss computed from a deep network, and reconstruct the blending region by iteratively updating the pixels using the L-BFGS solver. In the blending image, we not only smooth out gradient domain of the blending boundary but also add consistent texture into the blending region. User studies show that our method outperforms strong baselines as well as state-of-the-art approaches when placing objects onto both paintings and real-world images.