Pluralistic Aging Diffusion Autoencoder
- Resource Type
- Conference
- Authors
- Li, Peipei; Wang, Rui; Huang, Huaibo; He, Ran; He, Zhaofeng
- Source
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV) ICCV Computer Vision (ICCV), 2023 IEEE/CVF International Conference on. :22556-22566 Oct, 2023
- Subject
- Computing and Processing
Signal Processing and Analysis
Computer vision
Noise reduction
Semantics
Stochastic processes
Estimation
Aging
Probabilistic logic
- Language
- ISSN
- 2380-7504
Face aging is an ill-posed problem because multiple plausible aging patterns may correspond to a given input. Most existing methods often produce one deterministic estimation. This paper proposes a novel CLIP-driven Pluralistic Aging Diffusion Autoencoder (PADA) to enhance the diversity of aging patterns. First, we employ diffusion models to generate diverse low-level aging details via a sequential denoising reverse process. Second, we present Probabilistic Aging Embedding (PAE) to capture diverse high-level aging patterns, which represents age information as probabilistic distributions in the common CLIP latent space. A text-guided KL-divergence loss is designed to guide this learning. Our method can achieve pluralistic face aging conditioned on open-world aging texts and arbitrary unseen face images. Qualitative and quantitative experiments demonstrate that our method can generate more diverse and high-quality plausible aging results.