π Geometric Computer Vision Library for Spatial AI
Python artificial-intelligencecomputer-visiondeep-learninghacktoberfestimage-processingmachine-learningneural-networkpythonpytorchroboticsspatial-ai
Preserve tensor principal-point gradients in camera construction (#6304)
A Aswanth Rajde3347bddc41
diff --git a/changelog.d/6304.fixed.md b/changelog.d/6304.fixed.mdnew file mode 100644index 000000000..1ed8e7f74--- /dev/null+++ b/changelog.d/6304.fixed.md@@ -0,0 +1 @@+`create_intrinsics` preserves gradients through tensor principal points instead of detaching them during camera construction.diff --git a/kornia/geometry/camera/utils.py b/kornia/geometry/camera/utils.pyindex 6a9ca5c2f..4af7716a8 100644--- a/kornia/geometry/camera/utils.py+++ b/kornia/geometry/camera/utils.py@@ -71,6 +71,8 @@ def create_intrinsics() -> torch.Tensor:"""Create intrinsic camera matrices from focal lengths and principal points.+ Tensor principal points retain their gradients in the returned matrices.+Args:fxs: Focal length in x directionfys: Focal length in y direction@@ -83,10 +85,7 @@ def create_intrinsics(Stacked intrinsic matrices of shape (N, 4, 4)"""intrinsics_batch: list[torch.Tensor] = []- # Convert cxs and cys to lists if they are tensors- cxs_list = cxs.tolist() if isinstance(cxs, torch.Tensor) else cxs- cys_list = cys.tolist() if isinstance(cys, torch.Tensor) else cys- for fx, fy, cx, cy in zip(fxs, fys, cxs_list, cys_list):+ for fx, fy, cx, cy in zip(fxs, fys, cxs, cys):intrinsics = torch.eye(4, device=device, dtype=dtype)intrinsics[0, 0] = fxintrinsics[1, 1] = fydiff --git a/tests/geometry/camera/test_pinhole.py b/tests/geometry/camera/test_pinhole.pyindex bf3f38389..21385e113 100644--- a/tests/geometry/camera/test_pinhole.py+++ b/tests/geometry/camera/test_pinhole.py@@ -23,12 +23,43 @@ import torchimport korniafrom kornia.geometry.camera.pinhole import PinholeCamerasList-from kornia.geometry.camera.utils import create_extrinsics_with_rotation, create_four_cameras, create_pinhole_camera+from kornia.geometry.camera.utils import (+ create_extrinsics_with_rotation,+ create_four_cameras,+ create_intrinsics,+ create_pinhole_camera,+)from testing.base import BaseTesterclass TestCameraFactories(BaseTester):+ @pytest.mark.parametrize("batch_size", [1, 2])+ def test_intrinsics_principal_point_gradients(self, batch_size, device, dtype):+ cx = torch.full((batch_size,), 319.5, device=device, dtype=dtype, requires_grad=True)+ cy = torch.full((batch_size,), 239.5, device=device, dtype=dtype, requires_grad=True)+ intrinsics = create_intrinsics([500.0] * batch_size, [600.0] * batch_size, cx, cy, device, dtype)+ assert intrinsics.requires_grad+ self.assert_close(intrinsics[:, 0, 2], cx)+ self.assert_close(intrinsics[:, 1, 2], cy)+ camera = kornia.geometry.camera.PinholeCamera(+ intrinsics,+ torch.eye(4, device=device, dtype=dtype).expand(batch_size, -1, -1),+ torch.full((batch_size,), 480.0, device=device, dtype=dtype),+ torch.full((batch_size,), 640.0, device=device, dtype=dtype),+ )+ points = torch.tensor([[[1.0, 2.0, 4.0], [2.0, 1.0, 2.0]]], device=device, dtype=dtype)+ gradients = torch.autograd.grad(camera.project(points.expand(batch_size, -1, -1)).sum(), (cx, cy))+ for gradient in gradients:+ self.assert_close(gradient, torch.full_like(cx, 2.0))++ def test_intrinsics_gradcheck(self, device):+ cx = torch.tensor([319.5, 315.25], device=device, dtype=torch.float64, requires_grad=True)+ cy = torch.tensor([239.5, 241.5], device=device, dtype=torch.float64, requires_grad=True)+ self.gradcheck(+ lambda cx, cy: create_intrinsics([500.0, 600.0], [550.0, 650.0], cx, cy, device, cx.dtype), (cx, cy)+ )+def test_float_angles(self, device: torch.device, dtype: torch.dtype) -> None:actual = create_extrinsics_with_rotation([0.0, math.pi / 2], [0.0, 0.0], [0.0, 0.0], [1.0, 2.0], [3.0, 4.0], [5.0, 6.0], device, dtype