# MureObjectStitch: Multi-reference Image Composition

Source: [MureObjectStitch: Multi-reference Image Composition](<https://www.sota2.com/research/paper/68fa77c11e209131cea751cc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:25:31.619Z

Authors: Jiaxuan Chen, Bo Zhang, Qingdong He, Jinlong Peng, Li Niu

Published: 2024-11-12T00:53:20.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Synthesis on MureCom](<https://www.sota2.com/research/sota/image-synthesis-on-murecom.md>): Image Synthesis; MureCom; CLIP-I: 0.8139.

- [Image Classification on DreamAssembly](<https://www.sota2.com/research/sota/image-classification-on-dreamassembly.md>): Image Classification; DreamAssembly; Accuracy: 68.

- [Image Synthesis on DreamAssembly (test)](<https://www.sota2.com/research/sota/image-synthesis-on-dreamassembly-test.md>): Image Synthesis; DreamAssembly (test); CLIP-I: 0.8033.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2411.07462>)

[PDF](<https://arxiv.org/pdf/2411.07462.pdf>)