用三模块设计实现高保真人脸生成，身份保留更精准。
MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation
- 分阶段处理：身份、光影、融合三模块协同生成
- 使用现成Controlnet，身份保留率优于现有产品
- 适合需要精准人脸复刻的数字人、虚拟形象应用
我们提出MegaPortrait，一种用于计算机视觉中个性化肖像生成的创新系统。该系统包含三个模块：身份网络（Identity Net）通过微调源图像生成学习到的身份特征；光影网络（Shading Net）利用提取的表征重新渲染肖像；融合网络（Harmonization Net）将粘贴的人脸与参考图像的身体融合，实现一致结果。本方法采用现成的Controlnets，在身份保留和图像保真度方面优于当前最先进的AI肖像产品。MegaPortrait设计简洁高效，通过与其它方法及产品的对比，验证了其优越性。
原文摘要 · Abstract (English)
We propose MegaPortrait. It's an innovative system for creating personalized portrait images in computer vision. It has three modules: Identity Net, Shading Net, and Harmonization Net. Identity Net generates learned identity using a customized model fine-tuned with source images. Shading Net re-renders portraits using extracted representations. Harmonization Net fuses pasted faces and the reference image's body for coherent results. Our approach with off-the-shelf Controlnets is better than state-of-the-art AI portrait products in identity preservation and image fidelity. MegaPortrait has a simple but effective design and we compare it with other methods and products to show its superiority.
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。