text23D
XPaperChallenge
3Dモデル生成
現在最強のText-to-3Dモデル"ProlificDreamer"をちゃんと理解する
https://zenn.dev/kamata1729/articles/55fda1a884bdfe
DreamFusion, Magic3D, Latent-NeRF, SJC, Dream3D, Fnatasia3D, Text2Room, ProlificDreamer
ProlificDreamerではMagic3Dと同様に、NeRFで学習→DMTetでmeshの学習の2-stageの学習方法を採用しています。
ProlificDreamer
https://ml.cs.tsinghua.edu.cn/prolificdreamer/
Variational Score Distillation
DreamFusion: Text-to-3D using 2D Diffusion
https://dreamfusion3d.github.io/
Meshy
https://www.meshy.ai/workspace/text-to-3d
テキスト to 3Dの生成AI「Rodin」オープントライアル開始！　ジオメトリ＆マテリアル生成からデータダウンロードまで無料で試用可能
https://cgworld.jp/flashnews/202406-AI-Rodin.html
Magic3D: High-Resolution Text-to-3D Content Creation
https://research.nvidia.com/labs/dir/magic3d/
AutoVFX
https://github.com/haoyuhsu/autovfx
https://arxiv.org/abs/2411.02394
GenXD: Generating Any 3D and 4D Scenes
https://arxiv.org/abs/2411.02319
DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion
https://github.com/wenqsun/DimensionX
text 2 CAD
https://note.com/chem_fac/n/n91d8acd4204d
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
https://guochengqian.github.io/project/magic123/
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
https://mrtornado24.github.io/DreamCraft3D/
Stable Zero123
https://ja.stability.ai/blog/stable-zero123-3d