# MureObjectStitch: Multi-reference Image Composition

arXiv: https://arxiv.org/abs/2411.07462 · HTML: https://mlsanity.com/paper/2411.07462/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 6 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Builds on (most cited first, 6 of 6)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [ControlCom: Controllable Image Composition using Diffusion Model](https://mlsanity.com/paper/2308.10040/) (2023)
- [ObjectStitch: Generative Object Compositing](https://mlsanity.com/paper/2212.00932/) (2022)
- [DreamCom: Finetuning Text-guided Inpainting Model for Image Composition](https://mlsanity.com/paper/2309.15508/) (2023)

## Built on by (most cited first, 4 of 4)

- [Does FLUX Already Know How to Perform Physically Plausible Image Composition?](https://mlsanity.com/paper/2509.21278/) (2025)
- [UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer](https://mlsanity.com/paper/2503.09277/) (2025)
- [ORIDa: Object-centric Real-world Image Composition Dataset](https://mlsanity.com/paper/2506.08964/) (2025)
- [MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation](https://mlsanity.com/paper/2505.21483/) (2025)

## Abstract (arXiv)

Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image. The existing methods are struggling to preserve the foreground details and adjust the foreground pose/viewpoint at the same time. In this work, we propose an effective finetuning strategy for generative image composition model, in which we finetune a pretrained model using one or more images containing the same foreground object. Moreover, we propose a multi-reference strategy, which allows the model to take in multiple reference images of the foreground object. The experiments on MureCOM dataset verify the effectiveness of our method. The code and model have been released at https://github.com/bcmi/MureObjectStitch-Image-Composition.