423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2026-03-03 02:35:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

rasterization header comment fixes

Browse Source 
Summary: Fix some missing or misplaced argument descriptions.

Reviewed By: nikhilaravi

Differential Revision: D31305132

fbshipit-source-id: af4fcee9766682b2b7f7f16327e839090e377be2
This commit is contained in:
Jeremy Reizenstein
2021-09-30 10:39:50 -07:00
committed by Facebook GitHub Bot
parent a5cbb624c1
commit 4ad8576541
4 changed files with 31 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
pytorch3d/csrc/rasterize_points/rasterize_points.h
View File

@@ -48,10 +48,10 @@ RasterizePointsNaiveCuda(
// in the batch where N is the batch size.
// num_points_per_cloud: LongTensor of shape (N) giving the number of points
// for each pointcloud in the batch.
// radius: FloatTensor of shape (P) giving the radius (in NDC units) of
// each point in points.
// image_size: Tuple (H, W) giving the size in pixels of the output
// image to be rasterized.
// radius: FloatTensor of shape (P) giving the radius (in NDC units) of
// each point in points.
// points_per_pixel: (K) The number closest of points to return for each pixel
//
// Returns:
@@ -126,11 +126,13 @@ torch::Tensor RasterizePointsCoarseCpu(
// in the batch where N is the batch size.
// num_points_per_cloud: LongTensor of shape (N) giving the number of points
// for each pointcloud in the batch.
// radius: FloatTensor of shape (P) giving the radius (in NDC units) of
// each point in points.
// image_size: Tuple (H, W) giving the size in pixels of the output
// image to be rasterized.
// radius: FloatTensor of shape (P) giving the radius (in NDC units) of
// each point in points.
// bin_size: Size of each bin within the image (in pixels)
// max_points_per_bin: The maximum number of points allowed to fall into each
// bin when using coarse-to-fine rasterization.
//
// Returns:
// points_per_bin: Tensor of shape (N, num_bins, num_bins) giving the number
@@ -303,10 +305,10 @@ torch::Tensor RasterizePointsBackward(
// in the batch where N is the batch size.
// num_points_per_cloud: LongTensor of shape (N) giving the number of points
// for each pointcloud in the batch.
// radius: FloatTensor of shape (P) giving the radius (in NDC units) of
// each point in points.
// image_size: Tuple (H, W) giving the size in pixels of the output
// image to be rasterized.
// radius: FloatTensor of shape (P) giving the radius (in NDC units) of
// each point in points.
// points_per_pixel: (K) The number of points to return for each pixel
// bin_size: Bin size (in pixels) for coarse-to-fine rasterization. Setting
// bin_size=0 uses naive rasterization instead.