LoginSignup
2
4

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

@H_satomi

[勉強会まとめ] Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images

Posted at

読んだ論文

論文(リンク)
作者のPix2Voxプロジェクト(リンク)

どんなもの？

  • 複数視点(3 view)2D画像から3D(ボクセル)を生成する
  • 従来のRNNを用いた手法(3D-R2N2など)の問題を解決した新しいフレームワークの提案
  • 従来手法(3D-R2N2)よりも24倍高速

技術や手法

OverView

68747470733a2f2f696e66696e6974657363726970742e636f6d2f776f726470726573732f77702d636f6e74656e742f75706c6f6164732f323031392f30342f50697832566f782d4f766572766965772e6a7067.jpg

Network Architecture

media_users_user_212769_project_334720_images_x2.png

###Context-aware Fusion
fig4.png

fig5.png

感想

文章には図の説明しか載ってなかったので省略しました。
こんなネットワーク構造の図を描きたい:worried:

(I.M)

2
4
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
Sign upLogin
2
4

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?