通过校准参考特征，实现前景细节保留与姿态调整的统一。
CareCom: Generative Image Composition with Calibrated Reference Features
- 引入多参考图像机制，支持任意数量前景参考图
- 校准全局与局部特征，提升与背景的适配性
- 适合需要精细控制前景姿态与细节的应用场景
图像合成旨在将前景对象无缝融合到背景中。尽管生成式图像合成取得显著进展，现有方法仍难以同时兼顾细节保留与前景姿态/视角调整。为此，我们扩展了现有生成合成模型至多参考版本，可使用任意数量的前景参考图像。进一步提出对前景参考图像的全局与局部特征进行校准，使其与背景信息兼容。校准后的参考特征能补充原始特征中合适的姿态与视角的全局和局部信息。在MVImgNet和MureCom上的大量实验表明，生成模型可显著受益于校准后的参考特征。
原文摘要 · Abstract (English)
Image composition aims to seamlessly insert foreground object into background. Despite the huge progress in generative image composition, the existing methods are still struggling with simultaneous detail preservation and foreground pose/view adjustment. To address this issue, we extend the existing generative composition model to multi-reference version, which allows using arbitrary number of foreground reference images. Furthermore, we propose to calibrate the global and local features of foreground reference images to make them compatible with the background information. The calibrated reference features can supplement the original reference features with useful global and local information of proper pose/view. Extensive experiments on MVImgNet and MureCom demonstrate that the generative model can greatly benefit from the calibrated reference features.
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。