Pluralistic Aging Diffusion Autoencoder
- URL: http://arxiv.org/abs/2303.11086v2
- Date: Thu, 24 Aug 2023 03:53:35 GMT
- Title: Pluralistic Aging Diffusion Autoencoder
- Authors: Peipei Li, Rui Wang, Huaibo Huang, Ran He, Zhaofeng He
- Abstract summary: Face aging is an ill-posed problem because multiple plausible aging patterns may correspond to a given input.
This paper proposes a novel CLIP-driven Pluralistic Aging Diffusion Autoencoder to enhance the diversity of aging patterns.
- Score: 63.50599304294062
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis [65.7968515029306]
We propose a novel Coarse-to-Fine Latent Diffusion (CFLD) method for Pose-Guided Person Image Synthesis (PGPIS)
A perception-refined decoder is designed to progressively refine a set of learnable queries and extract semantic understanding of person images as a coarse-grained prompt.
arXiv Detail & Related papers (2024-02-28T06:07:07Z) - CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using
Score-Based Diffusion Models [57.9771859175664]
Recent generative-prior-based methods have shown promising blind face restoration performance.
Generating fine-grained facial details faithful to inputs remains a challenging problem.
We introduce a diffusion-based-prior inside a VQGAN architecture that focuses on learning the distribution over uncorrupted latent embeddings.
arXiv Detail & Related papers (2024-02-08T23:51:49Z) - Diverse and Lifespan Facial Age Transformation Synthesis with Identity Variation Rationality Metric [12.438204529412706]
We introduce $rmDLATboldsymbol+$ to realize Diverse and Lifespan Age Transformation on human faces.
Apart from the diversity mechanism embedded in the model, multiple consistency restrictions are leveraged to keep it away from counterfactual aging syntheses.
arXiv Detail & Related papers (2024-01-25T09:26:08Z) - CILF-CIAE: CLIP-driven Image-Language Fusion for Correcting Inverse Age Estimation [14.158939954453933]
The age estimation task aims to predict the age of an individual by analyzing facial features in an image.
Existing CLIP-based age estimation methods require high memory usage and lack an error feedback mechanism.
We propose a novel CLIP-driven Image-Language Fusion for Correcting Inverse Age Estimation (CILF-CIAE)
arXiv Detail & Related papers (2023-12-04T09:35:36Z) - Face Aging via Diffusion-based Editing [5.318584973533008]
We propose FADING, a novel approach to address Face Aging via DIffusion-based editiNG.
We go beyond existing methods by leveraging the rich prior of large-scale language-image diffusion models.
Our method outperforms existing approaches with respect to aging accuracy, attribute preservation, and aging quality.
arXiv Detail & Related papers (2023-09-20T13:47:10Z) - Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text
Generation via Concentrating Attention [85.5379146125199]
Powerful Transformer architectures have proven superior in generating high-quality sentences.
In this work, we find that sparser attention values in Transformer could improve diversity.
We introduce a novel attention regularization loss to control the sharpness of the attention distribution.
arXiv Detail & Related papers (2022-11-14T07:53:16Z) - Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth
Uncertainty Learning [54.15303628138665]
Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks.
Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance.
We propose Dual Spoof Disentanglement Generation framework to tackle this challenge by "anti-spoofing via generation"
arXiv Detail & Related papers (2021-12-01T15:36:59Z) - Continuous Face Aging Generative Adversarial Networks [11.75204350455584]
Face aging is the task aiming to translate the faces in input images to designated ages.
Previous methods have limited themselves only able to produce discrete age groups, each of which consists of ten years.
We propose the continuous face aging generative adversarial networks (CFA-GAN)
arXiv Detail & Related papers (2021-02-26T06:22:25Z) - PFA-GAN: Progressive Face Aging with Generative Adversarial Network [19.45760984401544]
This paper proposes a novel progressive face aging framework based on generative adversarial network (PFA-GAN)
The framework can be trained in an end-to-end manner to eliminate accumulative artifacts and blurriness.
Extensively experimental results demonstrate superior performance over existing (c)GANs-based methods.
arXiv Detail & Related papers (2020-12-07T05:45:13Z) - Enhancing Facial Data Diversity with Style-based Face Aging [59.984134070735934]
In particular, face datasets are typically biased in terms of attributes such as gender, age, and race.
We propose a novel, generative style-based architecture for data augmentation that captures fine-grained aging patterns.
We show that the proposed method outperforms state-of-the-art algorithms for age transfer.
arXiv Detail & Related papers (2020-06-06T21:53:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.