423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-08-03 12:22:49 +08:00
Code Issues Packages Projects Releases Wiki Activity
pytorch3d/pytorch3d/csrc
History
Georgia Gkioxari d689baac5e fix alpha compositing 
Summary:
Fix division by zero when alpha is 1.0
In this case, the nominator is already 0 and we need to make sure division with 0 does not occur which would produce nans

Reviewed By: nikhilaravi

Differential Revision: D21650478

fbshipit-source-id: bc457105b3050fef1c8bd4e58e7d6d15c0c81ffd
2020-05-20 09:27:42 -07:00
..
compositing
fix alpha compositing
2020-05-20 09:27:42 -07:00
face_areas_normals
Make cuda tensors contiguous in host function and remove contiguous check
2020-05-15 15:00:25 -07:00
gather_scatter
Make cuda tensors contiguous in host function and remove contiguous check
2020-05-15 15:00:25 -07:00
knn
Make cuda tensors contiguous in host function and remove contiguous check
2020-05-15 15:00:25 -07:00
packed_to_padded_tensor
Make cuda tensors contiguous in host function and remove contiguous check
2020-05-15 15:00:25 -07:00
point_mesh
Make cuda tensors contiguous in host function and remove contiguous check
2020-05-15 15:00:25 -07:00
rasterize_meshes
Make cuda tensors contiguous in host function and remove contiguous check
2020-05-15 15:00:25 -07:00
rasterize_points
Make cuda tensors contiguous in host function and remove contiguous check
2020-05-15 15:00:25 -07:00
utils
Cuda updates
2020-04-24 09:11:04 -07:00
ext.cpp
Cuda updates
2020-04-24 09:11:04 -07:00