def test_smoke(self, device, dtype): P1 = torch.rand(1, 3, 4, device=device, dtype=dtype) P2 = torch.rand(1, 3, 4, device=device, dtype=dtype) points1 = torch.rand(1, 1, 2, device=device, dtype=dtype) points2 = torch.rand(1, 1, 2, device=device, dtype=dtype) points3d = epi.triangulate_points(P1, P2, points1, points2) assert points3d.shape == (1, 1, 3)
def test_shape(self, batch_size, num_points, device, dtype): B, N = batch_size, num_points P1 = torch.rand(B, 3, 4, device=device, dtype=dtype) P2 = torch.rand(1, 3, 4, device=device, dtype=dtype) points1 = torch.rand(1, N, 2, device=device, dtype=dtype) points2 = torch.rand(B, N, 2, device=device, dtype=dtype) points3d = epi.triangulate_points(P1, P2, points1, points2) assert points3d.shape == (B, N, 3)
def test_two_view(self, device, dtype): num_views: int = 2 num_points: int = 10 scene: Dict[str, torch.Tensor] = epi.generate_scene(num_views, num_points) P1 = scene['P'][0:1] P2 = scene['P'][1:2] x1 = scene['points2d'][0:1] x2 = scene['points2d'][1:2] X = epi.triangulate_points(P1, P2, x1, x2) x_reprojected = kornia.transform_points(scene['P'], X.expand(num_views, -1, -1)) assert_allclose(scene['points3d'], X, rtol=1e-4, atol=1e-4) assert_allclose(scene['points2d'], x_reprojected)