mirror of
https://github.com/facebookresearch/pytorch3d.git
synced 2025-08-02 03:42:50 +08:00
b19fe1de2f
Summary: This diff integrates the pulsar renderer source code into PyTorch3D as an alternative backend for the PyTorch3D point renderer. This diff is the first of a series of three diffs to complete that migration and focuses on the packaging and integration of the source code. For more information about the pulsar backend, see the release notes and the paper (https://arxiv.org/abs/2004.07484). For information on how to use the backend, see the point cloud rendering notebook and the examples in the folder `docs/examples`. Tasks addressed in the following diffs: * Add the PyTorch3D interface, * Add notebook examples and documentation (or adapt the existing ones to feature both interfaces). Reviewed By: nikhilaravi Differential Revision: D23947736 fbshipit-source-id: a5e77b53e6750334db22aefa89b4c079cda1b443
127 lines
3.8 KiB
Python
127 lines
3.8 KiB
Python
# Copyright (c) Facebook, Inc. and its affiliates. All rights reserved.
|
|
"""Tests for the orthogonal projection."""
|
|
import logging
|
|
import sys
|
|
import unittest
|
|
from os import path
|
|
|
|
import numpy as np
|
|
import torch
|
|
|
|
|
|
# Making sure you can run this, even if pulsar hasn't been installed yet.
|
|
sys.path.insert(0, path.join(path.dirname(__file__), ".."))
|
|
devices = [torch.device("cuda"), torch.device("cpu")]
|
|
|
|
|
|
class TestOrtho(unittest.TestCase):
|
|
"""Test the orthogonal projection."""
|
|
|
|
def test_basic(self):
|
|
"""Basic forward test of the orthogonal projection."""
|
|
from pytorch3d.renderer.points.pulsar import Renderer
|
|
|
|
n_points = 10
|
|
width = 1000
|
|
height = 1000
|
|
renderer_left = Renderer(
|
|
width,
|
|
height,
|
|
n_points,
|
|
right_handed_system=False,
|
|
orthogonal_projection=True,
|
|
)
|
|
renderer_right = Renderer(
|
|
width,
|
|
height,
|
|
n_points,
|
|
right_handed_system=True,
|
|
orthogonal_projection=True,
|
|
)
|
|
# Generate sample data.
|
|
torch.manual_seed(1)
|
|
vert_pos = torch.rand(n_points, 3, dtype=torch.float32) * 10.0
|
|
vert_pos[:, 2] += 25.0
|
|
vert_pos[:, :2] -= 5.0
|
|
vert_pos_neg = vert_pos.clone()
|
|
vert_pos_neg[:, 2] *= -1.0
|
|
vert_col = torch.rand(n_points, 3, dtype=torch.float32)
|
|
vert_rad = torch.rand(n_points, dtype=torch.float32)
|
|
cam_params = torch.tensor(
|
|
[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 20.0], dtype=torch.float32
|
|
)
|
|
for device in devices:
|
|
vert_pos = vert_pos.to(device)
|
|
vert_pos_neg = vert_pos_neg.to(device)
|
|
vert_col = vert_col.to(device)
|
|
vert_rad = vert_rad.to(device)
|
|
cam_params = cam_params.to(device)
|
|
renderer_left = renderer_left.to(device)
|
|
renderer_right = renderer_right.to(device)
|
|
result_left = (
|
|
renderer_left.forward(
|
|
vert_pos,
|
|
vert_col,
|
|
vert_rad,
|
|
cam_params,
|
|
1.0e-1,
|
|
45.0,
|
|
percent_allowed_difference=0.01,
|
|
)
|
|
.cpu()
|
|
.detach()
|
|
.numpy()
|
|
)
|
|
hits_left = (
|
|
renderer_left.forward(
|
|
vert_pos,
|
|
vert_col,
|
|
vert_rad,
|
|
cam_params,
|
|
1.0e-1,
|
|
45.0,
|
|
percent_allowed_difference=0.01,
|
|
mode=1,
|
|
)
|
|
.cpu()
|
|
.detach()
|
|
.numpy()
|
|
)
|
|
result_right = (
|
|
renderer_right.forward(
|
|
vert_pos_neg,
|
|
vert_col,
|
|
vert_rad,
|
|
cam_params,
|
|
1.0e-1,
|
|
45.0,
|
|
percent_allowed_difference=0.01,
|
|
)
|
|
.cpu()
|
|
.detach()
|
|
.numpy()
|
|
)
|
|
hits_right = (
|
|
renderer_right.forward(
|
|
vert_pos_neg,
|
|
vert_col,
|
|
vert_rad,
|
|
cam_params,
|
|
1.0e-1,
|
|
45.0,
|
|
percent_allowed_difference=0.01,
|
|
mode=1,
|
|
)
|
|
.cpu()
|
|
.detach()
|
|
.numpy()
|
|
)
|
|
self.assertTrue(np.allclose(result_left, result_right))
|
|
self.assertTrue(np.allclose(hits_left, hits_right))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
logging.basicConfig(level=logging.INFO)
|
|
logging.getLogger("pulsar.renderer").setLevel(logging.WARN)
|
|
unittest.main()
|