Files and links (1)
SubmittedarXiv.org - Non-exclusive license to distribute, Open
Conference proceeding
DCFace: Synthetic Face Generation with Dual Condition Diffusion Model
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 12715-12725
Jun 2023
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Generating synthetic datasets for training face recognition models is challenging because dataset generation entails more than creating high fidelity images. It involves generating multiple images of same subjects under different factors (e.g., variations in pose, illumination, expression, aging and occlusion) which follows the real image conditional distribution. Previous works have studied the generation of synthetic datasets using GAN or 3D models. In this work, we approach the problem from the aspect of combining subject appearance (ID) and external factor (style) conditions. These two conditions provide a direct way to control the inter-class and intra-class variations. To this end, we propose a Dual Condition Face Generator (DCFace) based on a diffusion model. Our novel Patch-wise style extractor and Time-step dependent ID loss enables DCFace to consistently produce face images of the same subject under different styles with precise control. Face recognition models trained on synthetic images from the proposed DCFace provide higher verification accuracies compared to previous works by 6.11% on average in 4 out of 5 test datasets, LFW, CFP-FP, CPLFW, AgeDB and CALFW. Code Link
Metrics
Details
- Title
- DCFace: Synthetic Face Generation with Dual Condition Diffusion Model
- Creators
- Minchul Kim - Michigan State UniversityFeng Liu - Michigan State UniversityAnil Jain - Michigan State UniversityFeng Liu - Drexel University, Computer ScienceXiaoming Liu - Michigan State University
- Publication Details
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 12715-12725
- Publisher
- IEEE
- Number of pages
- 11
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:001062522105004
- Scopus ID
- 2-s2.0-85218192794
- Other Identifier
- 991022008295704721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Artificial Intelligence