Difference between revisions of "Generative Facial Prior-Generative Adversarial Network (GFP-GAN)"
m |
m |
||
| Line 15: | Line 15: | ||
* [[Variational Autoencoder (VAE)]] | * [[Variational Autoencoder (VAE)]] | ||
* [[Generated Image]] | * [[Generated Image]] | ||
| + | * [http://arxiv.org/pdf/2101.04061.pdf Towards Real-World Blind Face Restoration with Generative Facial Prior Xintao Wang, Yu Li, Honglun Zhang, Ying Shan] | ||
Conventional methods fine-tune an existing AI model to restore images by gauging differences between the artificial and real photos. That frequently leads to low-quality results, the scientists said. The new approach uses a pre-trained version of an existing model (NVIDIA's StyleGAN-2) to inform the team's own model at multiple stages during the image generation process. The technique aims to preserve the "identity" of people in a photo, with a particular focus on facial features like eyes and mouths. | Conventional methods fine-tune an existing AI model to restore images by gauging differences between the artificial and real photos. That frequently leads to low-quality results, the scientists said. The new approach uses a pre-trained version of an existing model (NVIDIA's StyleGAN-2) to inform the team's own model at multiple stages during the image generation process. The technique aims to preserve the "identity" of people in a photo, with a particular focus on facial features like eyes and mouths. | ||
Revision as of 14:52, 31 July 2022
YouTube search... ...Google search
- Generative Adversarial Network (GAN)
- Semi-Supervised Learning with Generative Adversarial Network (SSL-GAN)
- Context-Conditional Generative Adversarial Network (CC-GAN)
- Image-to-Image Translation
- Autoencoder (AE) / Encoder-Decoder
- Variational Autoencoder (VAE)
- Generated Image
- Towards Real-World Blind Face Restoration with Generative Facial Prior Xintao Wang, Yu Li, Honglun Zhang, Ying Shan
Conventional methods fine-tune an existing AI model to restore images by gauging differences between the artificial and real photos. That frequently leads to low-quality results, the scientists said. The new approach uses a pre-trained version of an existing model (NVIDIA's StyleGAN-2) to inform the team's own model at multiple stages during the image generation process. The technique aims to preserve the "identity" of people in a photo, with a particular focus on facial features like eyes and mouths.
