423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-12-15 03:40:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

provide cow dataset

Browse Source 
Summary: Make a dummy single-scene dataset using the code from generate_cow_renders (used in existing NeRF tutorials)

Reviewed By: kjchalup

Differential Revision: D38116910

fbshipit-source-id: 8db6df7098aa221c81d392e5cd21b0e67f65bd70
This commit is contained in:
Jeremy Reizenstein
2022-08-01 01:52:12 -07:00
committed by Facebook GitHub Bot
parent 1b0584f7bd
commit 14bd5e28e8
9 changed files with 302 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/tutorials/data/cow_mesh/README.md
View File

@@ -1,5 +1,5 @@
# Acknowledgements
Thank you to Keenen Crane for allowing the cow mesh model to be used freely in the public domain.
Thank you to Keenan Crane for allowing the cow mesh model to be used freely in the public domain.
###### Source: http://www.cs.cmu.edu/~kmcrane/Projects/ModelRepository/

2
docs/tutorials/utils/generate_cow_renders.py
View File

@@ -44,6 +44,8 @@ def generate_cow_renders(
data_dir: The folder that contains the cow mesh files. If the cow mesh
files do not exist in the folder, this function will automatically
download them.
azimuth_range: number of degrees on each side of the start position to
take samples
Returns:
cameras: A batch of `num_views` `FoVPerspectiveCameras` from which the