Skip to search formSkip to main contentSkip to account menu
DOI:10.48550/arXiv.2405.00228 - Corpus ID: 269484750
@article{Geissbhler2024SyntheticFD, title={Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion}, author={David Geissb{\"u}hler and Hatef Otroshi-Shahreza and S{\'e}bastien Marcel}, journal={ArXiv}, year={2024}, volume={abs/2405.00228}, url={https://api.semanticscholar.org/CorpusID:269484750}}
- David Geissbühler, Hatef Otroshi-Shahreza, Sébastien Marcel
- Published in arXiv.org 30 April 2024
- Computer Science
A new method, inspired by the physical motion of soft particles subjected to stochastic Brownian forces, is introduced, allowing us to sample identities distributions in a latent space under various constraints, showing that data generated with this method exceeds the performance of previously GAN-based datasets and achieves competitive performance with state-of-the-art diffusion-based synthetic datasets.
Figures and Tables from this paper
- figure 1
- table 1
- figure 2
- table 2
- figure 3
- table 3
- figure 4
- table 4
- figure 5
- table 5
- table 6
- figure 6
- table 7
- figure 7
- table 8
- table 9
- table 10
Ask This Paper
BETA
AI-Powered
Ask This Paper
BETA
AI-Powered
Unknown Error
An unexpected error occurred. Please try again.
No Answer Found
Ask another question that can be answered by this paper or rephrase your question.
We are still processing this paper
Please try again later.
Question Answering Unavailable
Please try again later.
No Response
The server took too long to answer your question. You can either rephrase your question or wait until it is less busy.
AI-Generated
Thank you for your feedback!
We're sorry, something went wrong while submitting this feedback.
Thank you for your feedback!
We're sorry, something went wrong while submitting this feedback.
Supporting Statements
Our system tries to constrain to information found in this paper. Results quality may vary. Learn more about how we generate these answers.
Feedback?
76 References
- Laurent ColboisTiago de Freitas PereiraS. Marcel
- 2021
Computer Science
2021 IEEE International Joint Conference on…
This paper introduces the proposed methodology to generate a synthetic dataset, without the need for human intervention, by exploiting the latent structure of a StyleGAN2 model with multiple controlled factors of variation, and confirms that the generated synthetic identities are not data subjects from the GAN's training dataset.
- 25
- Highly Influential[PDF]
- Pietro MelziC. Rathgeb Maxim Schaubert
- 2023
Computer Science
2023 IEEE/CVF International Conference on…
The results show the feasibility of the proposed GANDiffFace, in particular the use of Diffusion models to enhance the (limited) intra-class variations provided by GANs towards the level of real-world datasets.
- 16 [PDF]
- Fadi BoutrosMarco HuberPatrick SiebkeTim RieberN. Damer
- 2022
Computer Science
2022 IEEE International Joint Conference on…
The reported evaluation results on five authentic face benchmarks demonstrated that the privacy-friendly synthetic dataset has a high potential to be used for training face recognition models, achieving, for example, a verification accuracy of 91.87% on LFW using multi-class classification and 99.13% using the combined learning strategy.
- 43 [PDF]
- J. KolfTim RieberJurek ElliesenFadi BoutrosArjan KuijperN. Damer
- 2023
Computer Science
2023 IEEE/CVF Conference on Computer Vision and…
This work presents a three-player generative adversarial network (GAN) framework, namely IDnet, that enables the integration of identity information into the generation process and empirically proved that the IDnet synthetic images are of higher identity discrimination in comparison to the conventional two-player GAN, while maintaining a realistic intra-identity variation.
- 11 [PDF]
- Fadi BoutrosMarcel KlemtMeiling FangArjan KuijperN. Damer
- 2023
Computer Science
2023 IEEE International Joint Conference on…
This work proposes a framework, ExFaceGAN, to disentangle identity information in pretrained GANs latent spaces, enabling the generation of multiple samples of any synthetic identity and demonstrates the generalizability and effectiveness of ExFaceGAN by integrating it into learned latent spaces of three SOTA GAN approaches.
- Fadi BoutrosJ. H. GrebeArjan KuijperN. Damer
- 2023
Computer Science
2023 IEEE/CVF International Conference on…
IDiff-Face is proposed, a novel approach based on conditional latent diffusion models for synthetic identity generation with realistic identity variations for face recognition training that pushed the limits of state-of-the-art performances.
- 17
- Highly Influential[PDF]
- Minchul KimFeng LiuAnil JainXiaoming Liu
- 2023
Computer Science
2023 IEEE/CVF Conference on Computer Vision and…
A Dual Condition Face Generator (DCFace) based on a diffusion model that enables DCFace to consistently produce face images of the same subject under different styles with precise control and provide higher verification accuracies compared to previous works.
- 40
- Highly Influential[PDF]
- Erroll WoodTadas Baltruvsaitis J. Shotton
- 2021
Computer Science
2021 IEEE/CVF International Conference on…
It is shown that it is possible to synthesize data with minimal domain gap, so that models trained on synthetic data generalize to real in-the-wild datasets and train machine learning systems for face-related tasks such as landmark localization and face parsing.
- 183 [PDF]
- Hatef Otroshi-ShahrezaChristophe Ecabert Julian Fiérrez
- 2024
Computer Science
ArXiv
An overview of the submitted face recognition models and reports achieved performance compared to baseline models trained on real and synthetic datasets is given and an outlook on the current state of the research in training face recognition models using synthetic data is presented.
- Haibo QiuBaosheng YuDihong GongZhifeng LiWei LiuD. Tao
- 2021
Computer Science
2021 IEEE/CVF International Conference on…
This paper first explores the performance gap between recent state-of-the-art face recognition models trained with synthetic and real face images, and devise the SynFace with identity mixup (IM) and domain mix up (DM) to mitigate the above performance gap.
- 79 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers