解决图像合成中真实性与细节保真难以兼顾的问题
OSInsert: Towards High-authenticity and High-fidelity Image Composition
- 分两阶段合成：先保证前景与背景协调性，再精细还原细节
- 在MureCOM数据集上实现高真实感与高保真度的统一
- 适合需要高质量图像合成的视觉生成研究者使用
生成式图像合成旨在将给定的前景对象重新融入背景图像，生成逼真的合成结果。现有方法要么注重前景姿态/视角与背景的一致性（高真实性），要么强调前景细节的准确保留（高保真度），但难以同时达成二者。本文提出一种两阶段策略：第一阶段采用高真实性方法生成合理的前景形状，作为第二阶段高保真方法的条件输入。在MureCOM数据集上的实验验证了该策略的有效性。代码与模型已开源至https://github.com/bcmi/OSInsert-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. Some high-authenticity methods can adjust foreground pose/view to be compatible with background, while some high-fidelity methods can preserve the foreground details accurately. However, existing methods can hardly achieve both goals at the same time. In this work, we propose a two-stage strategy to achieve both goals. In the first stage, we use high-authenticity method to generate reasonable foreground shape, serving as the condition of high-fidelity method in the second stage. The experiments on MureCOM dataset verify the effectiveness of our two-stage strategy. The code and model have been released at https://github.com/bcmi/OSInsert-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。