screen cameras lose -1

Summary:
All the renderers in PyTorch3D (pointclouds including pulsar, meshes, raysampling) use align_corners=False style. NDC space goes between the edges of the outer pixels. For a non square image with W>H, the vertical NDC space goes from -1 to 1 and the horizontal from -W/H to W/H.

However it was recently pointed out that functionality which deals with screen space inside the camera classes is inconsistent with this. It unintentionally uses align_corners=True. This fixes that.

This would change behaviour of the following:
- If you create a camera in screen coordinates, i.e. setting in_ndc=False, then anything you do with the camera which touches NDC space may be affected, including trying to use renderers. The transform_points_screen function will not be affected...
- If you call the function “transform_points_screen” on a camera defined in NDC space results will be different. I have illustrated in the diff how to get the old results from the new results but this probably isn’t the right long-term solution..

Reviewed By: gkioxari

Differential Revision: D32536305

fbshipit-source-id: 377325a9137282971dcb7ca11a6cba3fc700c9ce

tests/test_cameras.py

@@ -130,9 +130,9 @@ def ndc_to_screen_points_naive(points, imsize):
     """
     height, width = imsize.unbind(1)
     width = width.view(-1, 1)
-    half_width = (width - 1.0) / 2.0
+    half_width = width / 2.0
     height = height.view(-1, 1)
-    half_height = (height - 1.0) / 2.0
+    half_height = height / 2.0
 
     scale = (
         half_width * (height > width).float() + half_height * (height <= width).float()
@@ -524,7 +524,7 @@ class TestCamerasCommon(TestCaseMixin, unittest.TestCase):
             # (height, width)
             image_size = torch.randint(low=2, high=64, size=(batch_size, 2))
             # scale
-            scale = (image_size.min(dim=1, keepdim=True).values - 1.0) / 2.0
+            scale = (image_size.min(dim=1, keepdim=True).values) / 2.0
 
             ndc_cam_params["focal_length"] = fcl
             ndc_cam_params["principal_point"] = prc
@@ -533,7 +533,7 @@ class TestCamerasCommon(TestCaseMixin, unittest.TestCase):
             screen_cam_params["image_size"] = image_size
             screen_cam_params["focal_length"] = fcl * scale
             screen_cam_params["principal_point"] = (
-                image_size[:, [1, 0]] - 1.0
+                image_size[:, [1, 0]]
             ) / 2.0 - prc * scale
             screen_cam_params["in_ndc"] = False
         else:
@@ -821,7 +821,7 @@ class TestFoVPerspectiveProjection(TestCaseMixin, unittest.TestCase):
     def test_perspective_type(self):
         cam = FoVPerspectiveCameras(znear=1.0, zfar=10.0, fov=60.0)
         self.assertTrue(cam.is_perspective())
-        self.assertEquals(cam.get_znear(), 1.0)
+        self.assertEqual(cam.get_znear(), 1.0)
 
 
 ############################################################
@@ -917,7 +917,7 @@ class TestFoVOrthographicProjection(TestCaseMixin, unittest.TestCase):
     def test_perspective_type(self):
         cam = FoVOrthographicCameras(znear=1.0, zfar=10.0)
         self.assertFalse(cam.is_perspective())
-        self.assertEquals(cam.get_znear(), 1.0)
+        self.assertEqual(cam.get_znear(), 1.0)
 
 
 ############################################################
@@ -974,7 +974,7 @@ class TestOrthographicProjection(TestCaseMixin, unittest.TestCase):
     def test_perspective_type(self):
         cam = OrthographicCameras(focal_length=5.0, principal_point=((2.5, 2.5),))
         self.assertFalse(cam.is_perspective())
-        self.assertEquals(cam.get_znear(), None)
+        self.assertIsNone(cam.get_znear())
 
 
 ############################################################
@@ -1026,4 +1026,4 @@ class TestPerspectiveProjection(TestCaseMixin, unittest.TestCase):
     def test_perspective_type(self):
         cam = PerspectiveCameras(focal_length=5.0, principal_point=((2.5, 2.5),))
         self.assertTrue(cam.is_perspective())
-        self.assertEquals(cam.get_znear(), None)
+        self.assertIsNone(cam.get_znear())

tests/test_render_meshes.py

@@ -250,23 +250,14 @@ class TestRenderMeshes(TestCaseMixin, unittest.TestCase):
         raster_settings = RasterizationSettings(
             image_size=512, blur_radius=0.0, faces_per_pixel=1
         )
+        half_half = (512.0 / 2.0, 512.0 / 2.0)
         for cam_type in (PerspectiveCameras, OrthographicCameras):
             cameras = cam_type(
                 device=device,
                 R=R,
                 T=T,
-                principal_point=(
-                    (
-                        (512.0 - 1.0) / 2.0,
-                        (512.0 - 1.0) / 2.0,
-                    ),
-                ),
-                focal_length=(
-                    (
-                        (512.0 - 1.0) / 2.0,
-                        (512.0 - 1.0) / 2.0,
-                    ),
-                ),
+                principal_point=(half_half,),
+                focal_length=(half_half,),
                 image_size=((512, 512),),
                 in_ndc=False,
             )
@@ -285,6 +276,10 @@ class TestRenderMeshes(TestCaseMixin, unittest.TestCase):
             images = renderer(sphere_mesh)
             rgb = images[0, ..., :3].squeeze().cpu()
             filename = "test_simple_sphere_light_phong_%s.png" % cam_type.__name__
+            if DEBUG:
+                Image.fromarray((rgb.numpy() * 255).astype(np.uint8)).save(
+                    DATA_DIR / f"{filename}_.png"
+                )
 
             image_ref = load_rgb_image(filename, DATA_DIR)
             self.assertClose(rgb, image_ref, atol=0.05)