[CVPR2022] FENeRF: Face Editing in Neural Radiance Fields
[CVPR2022] FENeRF: Face Editing in Neural Radiance Fields
|
CV |
0 评论
Introduction关于肖像生成的方法,目前主要有两种,2D GANs和3D-aware GANs,两者各有擅长的方面。2D GAN可以生成高分辨率图像并具有很高的可编辑性,但是生成不同视图时的一致性很差,3D-aware GAN则相反,能生成一致性很高的视图,但是视图的分辨率和可编辑性不高该文
[CVPR2022] High-Resolution Image Synthesis with Latent Diffusion Models
[CVPR2022] High-Resolution Image Synthesis with Latent Diffusion Models
|
CV |
0 评论
latent-diffusion
[NeurIPS2020] Denoising Diffusion Probabilistic Models
[NeurIPS2020] Denoising Diffusion Probabilistic Models
|
CV |
0 评论
DDPM
DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis
DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis
|
CV |
0 评论
A Simple and Effective Baseline for Text-to-Image Synthesis
[ECCV2022] CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer
[ECCV2022] CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer
|
CV |
0 评论
一种通用的风格转移方法,可以实现艺术、逼真的风格迁移,以及实现视频的风格迁移,同时在训练过程中并没有视频的参与
Demystifying Neural Style Transfer
Demystifying Neural Style Transfer
|
Style transfer is essentially a domain adaptation problem, which aligns the feature distributions.
基于CLIPstyler的研究过程记录
基于CLIPstyler的研究过程记录
|
CV |
0 评论
对CLIPstyler进行研究的过程记录
[CVPR2022] CLIPstyler: Image Style Transfer with a Single Text Condition
[CVPR2022] CLIPstyler: Image Style Transfer with a Single Text Condition
|
CV |
0 评论
使用CLIP进行风格迁移
[arXiv] Pivotal Tuning for Latent-based Editing of Real Images
[arXiv] Pivotal Tuning for Latent-based Editing of Real Images
|
基于优化的,更新StyleGAN参数的反演方法
服务器使用文档
服务器使用文档
|
CV Life |
0 评论
服务器使用文档