423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-12-20 22:30:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

camera refactoring

Browse Source 
Summary:
Refactor cameras
* CamerasBase was enhanced with `transform_points_screen` that transforms projected points from NDC to screen space
* OpenGLPerspective, OpenGLOrthographic -> FoVPerspective, FoVOrthographic
* SfMPerspective, SfMOrthographic -> Perspective, Orthographic
* PerspectiveCamera can optionally be constructred with screen space parameters
* Note on Cameras and coordinate systems was added

Reviewed By: nikhilaravi

Differential Revision: D23168525

fbshipit-source-id: dd138e2b2cc7e0e0d9f34c45b8251c01266a2063
This commit is contained in:
Georgia Gkioxari
2020-08-20 22:20:41 -07:00
committed by Facebook GitHub Bot
parent 9242e7e65d
commit 57a22e7306
65 changed files with 896 additions and 279 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/test_r2n2.py
View File

@@ -18,7 +18,7 @@ from pytorch3d.datasets import (
render_cubified_voxels,
)
from pytorch3d.renderer import (
OpenGLPerspectiveCameras,
FoVPerspectiveCameras,
PointLights,
RasterizationSettings,
look_at_view_transform,
@@ -211,7 +211,7 @@ class TestR2N2(TestCaseMixin, unittest.TestCase):
# Render first three models in the dataset.
R, T = look_at_view_transform(1.0, 1.0, 90)
cameras = OpenGLPerspectiveCameras(R=R, T=T, device=device)
cameras = FoVPerspectiveCameras(R=R, T=T, device=device)
raster_settings = RasterizationSettings(image_size=512)
lights = PointLights(
location=torch.tensor([0.0, 1.0, -2.0], device=device)[None],