用多参考图提升生成图像拼接的细节与视角一致性。
MureObjectStitch: Multi-reference Image Composition
- 通过多个参考图微调预训练模型，增强前景细节保留能力。
- 在MureCOM数据集上实现更自然的物体姿态与背景融合效果。
- 适合需要精准控制物体外观和视角的应用场景。
生成式图像拼接旨在将给定前景物体重新生成到背景图像中，形成逼真的合成图像。现有方法难以同时保持前景细节并调整其姿态或视角。本文提出一种高效的生成图像拼接模型微调策略，利用包含相同前景物体的一张或多张参考图像对预训练模型进行微调。进一步提出多参考策略，使模型可同时处理多个前景物体参考图像。在MureCOM数据集上的实验验证了该方法的有效性。代码与模型已开源：https://github.com/bcmi/MureObjectStitch-Image-Composition。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。