423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-12-20 14:20:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

Blending fixes and test updates

Browse Source 
Summary:
Changed `torch.cumprod` to `torch.prod` in blending functions and added more tests and benchmark tests.

This should fix the issue raised on GitHub.

Reviewed By: gkioxari

Differential Revision: D20163073

fbshipit-source-id: 4569fd37be11aa4435a3ce8736b55622c00ec718
This commit is contained in:
Nikhila Ravi
2020-02-29 17:49:14 -08:00
committed by Facebook Github Bot
parent ff19c642cb
commit ba11c0b59c
3 changed files with 312 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
pytorch3d/renderer/blending.py
View File

@@ -45,7 +45,7 @@ def sigmoid_alpha_blend(colors, fragments, blend_params) -> torch.Tensor:
"""
Silhouette blending to return an RGBA image
- **RGB** - choose color of the closest point.
- **A** - blend based on the 2D distance based probability map [0].
- **A** - blend based on the 2D distance based probability map [1].
Args:
colors: (N, H, W, K, 3) RGB color for each of the top K faces per pixel.
@@ -60,7 +60,7 @@ def sigmoid_alpha_blend(colors, fragments, blend_params) -> torch.Tensor:
Returns:
RGBA pixel_colors: (N, H, W, 4)
[0] Liu et al, 'Soft Rasterizer: A Differentiable Renderer for Image-based
[1] Liu et al, 'Soft Rasterizer: A Differentiable Renderer for Image-based
3D Reasoning', ICCV 2019
"""
N, H, W, K = fragments.pix_to_face.shape
@@ -73,20 +73,13 @@ def sigmoid_alpha_blend(colors, fragments, blend_params) -> torch.Tensor:
# the face. Therefore use -1.0 * fragments.dists to get the correct sign.
prob = torch.sigmoid(-fragments.dists / blend_params.sigma) * mask
# The cumulative product ensures that alpha will be 1 if at least 1 face
# fully covers the pixel as for that face prob will be 1.0
# TODO: investigate why torch.cumprod backwards is very slow for large
# values of K.
# Temporarily replace this with exp(sum(log))) using the fact that
# a*b = exp(log(a*b)) = exp(log(a) + log(b))
# alpha = 1.0 - torch.cumprod((1.0 - prob), dim=-1)[..., -1]
alpha = 1.0 - torch.exp(torch.log((1.0 - prob)).sum(dim=-1))
# The cumulative product ensures that alpha will be 0.0 if at least 1
# face fully covers the pixel as for that face, prob will be 1.0.
# This results in a multiplication by 0.0 because of the (1.0 - prob)
# term. Therefore 1.0 - alpha will be 1.0.
alpha = torch.prod((1.0 - prob), dim=-1)
pixel_colors[..., :3] = colors[..., 0, :] # Hard assign for RGB
pixel_colors[..., 3] = alpha
pixel_colors = torch.clamp(pixel_colors, min=0, max=1.0)
pixel_colors[..., 3] = 1.0 - alpha
return torch.flip(pixel_colors, [1])
@@ -95,7 +88,7 @@ def softmax_rgb_blend(
) -> torch.Tensor:
"""
RGB and alpha channel blending to return an RGBA image based on the method
proposed in [0]
proposed in [1]
- **RGB** - blend the colors based on the 2D distance based probability map and
relative z distances.
- **A** - blend based on the 2D distance based probability map.
@@ -151,15 +144,11 @@ def softmax_rgb_blend(
# Sigmoid probability map based on the distance of the pixel to the face.
prob_map = torch.sigmoid(-fragments.dists / blend_params.sigma) * mask
# The cumulative product ensures that alpha will be 1 if at least 1 face
# fully covers the pixel as for that face prob will be 1.0
# TODO: investigate why torch.cumprod backwards is very slow for large
# values of K.
# Temporarily replace this with exp(sum(log))) using the fact that
# a*b = exp(log(a*b)) = exp(log(a) + log(b))
# alpha = 1.0 - torch.cumprod((1.0 - prob), dim=-1)[..., -1]
alpha = 1.0 - torch.exp(torch.log((1.0 - prob_map)).sum(dim=-1))
# The cumulative product ensures that alpha will be 0.0 if at least 1
# face fully covers the pixel as for that face, prob will be 1.0.
# This results in a multiplication by 0.0 because of the (1.0 - prob)
# term. Therefore 1.0 - alpha will be 1.0.
alpha = torch.prod((1.0 - prob_map), dim=-1)
# Weights for each face. Adjust the exponential by the max z to prevent
# overflow. zbuf shape (N, H, W, K), find max over K.
@@ -178,8 +167,6 @@ def softmax_rgb_blend(
weighted_colors = (weights[..., None] * colors).sum(dim=-2)
weighted_background = (delta / denom) * background
pix_colors[..., :3] = weighted_colors + weighted_background
pix_colors[..., 3] = alpha
pix_colors[..., 3] = 1.0 - alpha
# Clamp colors to the range 0-1 and flip y axis.
pix_colors = torch.clamp(pix_colors, min=0, max=1.0)
return torch.flip(pix_colors, [1])