Deepfake for the Good: Generating Avatars through Face-Swapping with Implicit Deepfake Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913592691916800 |
|---|---|
| author | Stanishevskii, Georgii Steczkiewicz, Jakub Szczepanik, Tomasz Tadeja, Sławomir Tabor, Jacek Spurek, Przemysław |
| author_facet | Stanishevskii, Georgii Steczkiewicz, Jakub Szczepanik, Tomasz Tadeja, Sławomir Tabor, Jacek Spurek, Przemysław |
| contents | Numerous emerging deep-learning techniques have had a substantial impact on computer graphics. Among the most promising breakthroughs are the rise of Neural Radiance Fields (NeRFs) and Gaussian Splatting (GS). NeRFs encode the object's shape and color in neural network weights using a handful of images with known camera positions to generate novel views. In contrast, GS provides accelerated training and inference without a decrease in rendering quality by encoding the object's characteristics in a collection of Gaussian distributions. These two techniques have found many use cases in spatial computing and other domains. On the other hand, the emergence of deepfake methods has sparked considerable controversy. Deepfakes refers to artificial intelligence-generated videos that closely mimic authentic footage. Using generative models, they can modify facial features, enabling the creation of altered identities or expressions that exhibit a remarkably realistic appearance to a real person. Despite these controversies, deepfake can offer a next-generation solution for avatar creation and gaming when of desirable quality. To that end, we show how to combine all these emerging technologies to obtain a more plausible outcome. Our ImplicitDeepfake uses the classical deepfake algorithm to modify all training images separately and then train NeRF and GS on modified faces. Such simple strategies can produce plausible 3D deepfake-based avatars. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_06390 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deepfake for the Good: Generating Avatars through Face-Swapping with Implicit Deepfake Generation Stanishevskii, Georgii Steczkiewicz, Jakub Szczepanik, Tomasz Tadeja, Sławomir Tabor, Jacek Spurek, Przemysław Computer Vision and Pattern Recognition Numerous emerging deep-learning techniques have had a substantial impact on computer graphics. Among the most promising breakthroughs are the rise of Neural Radiance Fields (NeRFs) and Gaussian Splatting (GS). NeRFs encode the object's shape and color in neural network weights using a handful of images with known camera positions to generate novel views. In contrast, GS provides accelerated training and inference without a decrease in rendering quality by encoding the object's characteristics in a collection of Gaussian distributions. These two techniques have found many use cases in spatial computing and other domains. On the other hand, the emergence of deepfake methods has sparked considerable controversy. Deepfakes refers to artificial intelligence-generated videos that closely mimic authentic footage. Using generative models, they can modify facial features, enabling the creation of altered identities or expressions that exhibit a remarkably realistic appearance to a real person. Despite these controversies, deepfake can offer a next-generation solution for avatar creation and gaming when of desirable quality. To that end, we show how to combine all these emerging technologies to obtain a more plausible outcome. Our ImplicitDeepfake uses the classical deepfake algorithm to modify all training images separately and then train NeRF and GS on modified faces. Such simple strategies can produce plausible 3D deepfake-based avatars. |
| title | Deepfake for the Good: Generating Avatars through Face-Swapping with Implicit Deepfake Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.06390 |