Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909388249235456 |
|---|---|
| author | Dong, Chengdong Bhagavatula, Vijayakumar Zhou, Zhenyu Kumar, Ajay |
| author_facet | Dong, Chengdong Bhagavatula, Vijayakumar Zhou, Zhenyu Kumar, Ajay |
| contents | The remarkable progress in neural-network-driven visual data generation, especially with neural rendering techniques like Neural Radiance Fields and 3D Gaussian splatting, offers a powerful alternative to GANs and diffusion models. These methods can produce high-fidelity images and lifelike avatars, highlighting the need for robust detection methods. In response, an unsupervised training technique is proposed that enables the model to extract comprehensive features from the Fourier spectrum magnitude, thereby overcoming the challenges of reconstructing the spectrum due to its centrosymmetric properties. By leveraging the spectral domain and dynamically combining it with spatial domain information, we create a robust multimodal detector that demonstrates superior generalization capabilities in identifying challenging synthetic images generated by the latest image synthesis techniques. To address the absence of a 3D neural rendering-based fake image database, we develop a comprehensive database that includes images generated by diverse neural rendering techniques, providing a robust foundation for evaluating and advancing detection methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_08642 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models Dong, Chengdong Bhagavatula, Vijayakumar Zhou, Zhenyu Kumar, Ajay Computer Vision and Pattern Recognition Artificial Intelligence The remarkable progress in neural-network-driven visual data generation, especially with neural rendering techniques like Neural Radiance Fields and 3D Gaussian splatting, offers a powerful alternative to GANs and diffusion models. These methods can produce high-fidelity images and lifelike avatars, highlighting the need for robust detection methods. In response, an unsupervised training technique is proposed that enables the model to extract comprehensive features from the Fourier spectrum magnitude, thereby overcoming the challenges of reconstructing the spectrum due to its centrosymmetric properties. By leveraging the spectral domain and dynamically combining it with spatial domain information, we create a robust multimodal detector that demonstrates superior generalization capabilities in identifying challenging synthetic images generated by the latest image synthesis techniques. To address the absence of a 3D neural rendering-based fake image database, we develop a comprehensive database that includes images generated by diverse neural rendering techniques, providing a robust foundation for evaluating and advancing detection methods. |
| title | Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2411.08642 |