#contents
----
* 概要 [#vcf3bb76]
* 手法比較 [#zf6433a4]
** Image Generation [#e1c949fa]
|名称|開発者|発表|概要|リンク|h
|GAN|Ian J. Goodfellow|2014|||
|StyleGAN|NVIDIA|2018|||
** Text to Image [#c05a9630]
|名称|開発者|発表|概要|リンク|h
|DALL-E|OpenAI|2021|||
|Imagen|Google|2022|||
|Midjourney|Midjourney|2022|||
|StableDiffusion|Stability AI|2022|||
- [[Tutorial on Diffusion Models for Imaging and Vision>https://arxiv.org/abs/2403.18103]]
** 2D to 3D [#l9f74658]
|名称|開発者|発表|概要|リンク|h
|[[pixelNeRF>https://github.com/sxyu/pixel-nerf]]||CVPR2021||[[!>https://alexyu.net/pixelnerf/]]|
|[[Depth Anything>https://github.com/LiheYoung/Depth-Anything]]||||[[!>https://arxiv.org/abs/2401.10891]]|
** Text to 3D [#l309b1e2]
|名称|開発者|発表|概要|リンク|h
|[[GaussianDreamer>https://github.com/hustvl/GaussianDreamer]]||2024||[[!>https://arxiv.org/abs/2310.08529]]|
