# Pluralistic Aging Diffusion Autoencoder

Source: [Pluralistic Aging Diffusion Autoencoder](<https://www.sota2.com/research/paper/68fa70671e209131cea4af08>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:41:08.783Z

Authors: Peipei Li, Rui Wang, Huaibo Huang, Ran He, Zhaofeng He

Published: 2023-03-20T13:20:14.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Face Aging on FFHQ-AT (test)](<https://www.sota2.com/research/sota/face-aging-on-ffhq-at-test.md>): Face Aging; FFHQ-AT (test); Age MAE: 3.09.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2303.11086>)

[PDF](<https://arxiv.org/pdf/2303.11086.pdf>)