用扩散模型局部老化人脸，实现更自然的个性化衰老效果。
Locally Controlled Face Aging with Latent Diffusion Models
- 基于潜在扩散模型，按面部区域分别控制老化过程。
- 保留身份特征，生成图像真实且老化过程可控。
- 适合需要精准老化模拟的研究与应用，如影视特效。
我们提出一种新方法解决现有面部老化技术将衰老视为全局均质过程的局限性。当前基于GAN和扩散模型的方法通常以参考图像和目标年龄为条件，忽略了面部区域因内在年龄因素和外部环境（如日晒）导致的老化异质性。本文利用潜在扩散模型，通过局部老化特征选择性地对特定面部区域进行老化处理。该方法显著提升了生成过程的细粒度控制能力，实现了更真实、个性化的老化效果。我们采用潜在扩散精炼器，无缝融合局部老化区域，确保整体合成结果在全局上一致且自然。实验表明，本方法有效满足成功面部老化的三个关键标准：强身份保持能力、高保真度与真实感图像，以及自然可控的衰老进程。
原文摘要 · Abstract (English)
We present a novel approach to face aging that addresses the limitations of current methods which treat aging as a global, homogeneous process. Existing techniques using GANs and diffusion models often condition generation on a reference image and target age, neglecting that facial regions age heterogeneously due to both intrinsic chronological factors and extrinsic elements like sun exposure. Our method leverages latent diffusion models to selectively age specific facial regions using local aging signs. This approach provides significantly finer-grained control over the generation process, enabling more realistic and personalized aging. We employ a latent diffusion refiner to seamlessly blend these locally aged regions, ensuring a globally consistent and natural-looking synthesis. Experimental results demonstrate that our method effectively achieves three key criteria for successful face aging: robust identity preservation, high-fidelity and realistic imagery, and a natural, controllable aging progression.
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。