Summary:
Use PyTorch3D's new faster sample_pdf function instead of local Python implementation.
Also clarify deps for the Python implementation.
Reviewed By: gkioxari
Differential Revision: D30512109
fbshipit-source-id: 84cfdc00313fada37a6b29837de96f6a4646434f
Summary: New test that each subpackage of pytorch3d imports cleanly.
Reviewed By: patricklabatut
Differential Revision: D30001632
fbshipit-source-id: ca8dcac94491fc22f33602b3bbef481cba927094
Summary: Implement the sample_pdf function from the NeRF project as compiled operators.. The binary search (in searchsorted) is replaced with a low tech linear search, but this is not a problem for the envisaged numbers of bins.
Reviewed By: gkioxari
Differential Revision: D26312535
fbshipit-source-id: df1c3119cd63d944380ed1b2657b6ad81d743e49
Summary: Copy the sample_pdf operation from the NeRF project in to PyTorch3D, in preparation for optimizing it.
Reviewed By: gkioxari
Differential Revision: D27117930
fbshipit-source-id: 20286b007f589a4c4d53ed818c4bc5f2abd22833
Summary: Fixes to a couple of comments on points to volumes, make the mask work in round_points_to_volumes, and remove a duplicate rand calculation
Reviewed By: nikhilaravi
Differential Revision: D29522845
fbshipit-source-id: 86770ba37ef3942b909baf63fd73eed1399635b6
Summary: Much of the code is actually available during the conda tests, as long as we look in the right place. We enable some of them.
Reviewed By: nikhilaravi
Differential Revision: D30249357
fbshipit-source-id: 01c57b6b8c04442237965f23eded594aeb90abfb
Summary:
Implementation of ball query from PointNet++. This function is similar to KNN (find the neighbors in p2 for all points in p1). These are the key differences:
- It will return the **first** K neighbors within a specified radius as opposed to the **closest** K neighbors.
- As all the points in p2 do not need to be considered to find the closest K, the algorithm is much faster than KNN when p2 has a large number of points.
- The neighbors are not sorted
- Due to the radius threshold it is not guaranteed that there will be K neighbors even if there are more than K points in p2.
- The padding value for `idx` is -1 instead of 0.
# Note:
- Some of the code is very similar to KNN so it could be possible to modify the KNN forward kernels to support ball query.
- Some users might want to use kNN with ball query - for this we could provide a wrapper function around the current `knn_points` which enables applying the radius threshold afterwards as an alternative. This could be called `ball_query_knn`.
Reviewed By: jcjohnson
Differential Revision: D30261362
fbshipit-source-id: 66b6a7e0114beff7164daf7eba21546ff41ec450
Summary: New test that notes and tutorials are listed in the website metadata, so that they will be included in the website build.
Reviewed By: nikhilaravi
Differential Revision: D30223799
fbshipit-source-id: 2dca9730b54e68da2fd430a7b47cb7e18814d518
Summary: Fix to resolve GitHub issue #796 - the cameras were being passed in the renderer forward pass instead of at initialization. The rasterizer was correctly using the cameras passed in the `kwargs` for the projection, but the `cameras` are still part of the `kwargs` for the `get_screen_to_ndc_transform` and `get_ndc_to_screen_transform` functions which is causing issues about duplicate arguments.
Reviewed By: bottler
Differential Revision: D30175679
fbshipit-source-id: 547e88d8439456e728fa2772722df5fa0fe4584d
Summary:
API fix for NDC/screen cameras and compatibility with PyTorch3D renderers.
With this new fix:
* Users can define cameras and `transform_points` under any coordinate system conventions. The transformation applies the camera K and RT to the input points, not regarding for PyTorch3D conventions. So this makes cameras completely independent from PyTorch3D renderer.
* Cameras can be defined either in NDC space or screen space. For existing ones, FoV cameras are in NDC space. Perspective/Orthographic can be defined in NDC or screen space.
* The interface with PyTorch3D renderers happens through `transform_points_ndc` which transforms points to the NDC space and assumes that input points are provided according to PyTorch3D conventions.
* Similarly, `transform_points_screen` transforms points to screen space and again assumes that input points are under PyTorch3D conventions.
* For Orthographic/Perspective cameras, if they are defined in screen space, the `get_ndc_camera_transform` allows points to be converted to NDC for use for the renderers.
Reviewed By: nikhilaravi
Differential Revision: D26932657
fbshipit-source-id: 1a964e3e7caa54d10c792cf39c4d527ba2fb2e79
Summary: A bad env var check meant these tests were not being run. Fix that, and fix the copyright test for the new message format.
Reviewed By: patricklabatut
Differential Revision: D29734562
fbshipit-source-id: a1a9bb68901b09c71c7b4ff81a04083febca8d50
Summary:
# Background
There is an unstable error during training (it can happen after several minutes or after several hours).
The error is connected to `torch.det()` function in `_check_valid_rotation_matrix()`.
if I remove the function `torch.det()` in `_check_valid_rotation_matrix()` or remove the whole functions `_check_valid_rotation_matrix()` the error is disappeared (D29555876).
# Solution
Replace `torch.det()` with manual implementation for 3x3 matrix.
Reviewed By: patricklabatut
Differential Revision: D29655924
fbshipit-source-id: 41bde1119274a705ab849751ece28873d2c45155
Summary:
Context: in the code we are releasing with CO3D dataset, we use `cuda()` on TensorProperties like Pointclouds and Cameras where we recursively move batch to a GPU. It would be good to push it to a release so we don’t need to depend on the nightly build.
Additionally, I aligned the logic of `.to("cuda")` without device index to the one of `torch.Tensor` where the current device is populated to index. It should not affect any actual use cases but some tests had to be changed.
Reviewed By: bottler
Differential Revision: D29659529
fbshipit-source-id: abe58aeaca14bacc68da3e6cf5ae07df3353e3ce
Summary: This commit adds a new camera conversion function for OpenCV style parameters to Pulsar parameters to the library. Using this function it addresses a bug reported here: https://fb.workplace.com/groups/629644647557365/posts/1079637302558095, by using the PyTorch3D->OpenCV->Pulsar chain instead of the original direct conversion function. Both conversions are well-tested and an additional test for the full chain has been added, resulting in a more reliable solution requiring less code.
Reviewed By: patricklabatut
Differential Revision: D29322106
fbshipit-source-id: 13df13c2e48f628f75d9f44f19ff7f1646fb7ebd
Summary: Use rotation matrices for OpenCV / PyTorch3D conversions: this avoids hiding issues with conversions to / from axis-angle vectors and ensure new conversion functions have a consistent interface.
Reviewed By: bottler, classner
Differential Revision: D29634099
fbshipit-source-id: 40b28357914eb563fedea60a965dcf69e848ccfa
Summary: Enable this benchmark to be run on its own, like others.
Reviewed By: patricklabatut
Differential Revision: D29522846
fbshipit-source-id: c7b3b5c9a0fcdeeb79d8b2ec197684b4380aa547
Summary: solve and lstsq have moved around in torch. Cope with both.
Reviewed By: patricklabatut
Differential Revision: D29302316
fbshipit-source-id: b34f0b923e90a357f20df359635929241eba6e74
Summary: Deprecate the `so3_exponential_map()` function in favor of its alias `so3_exp_map()`: this aligns with the naming of `so3_log_map()` and the recently introduced `se3_exp_map()` / `se3_log_map()` pair.
Reviewed By: bottler
Differential Revision: D29329966
fbshipit-source-id: b6f60b9e86b2995f70b1fbeb16f9feea05c55de9
Summary: Add functionality to to save an `.obj` file with associated UV textures: `.png` image and `.mtl` file as well as saving verts_uvs and faces_uvs to the `.obj` file.
Reviewed By: bottler
Differential Revision: D29337562
fbshipit-source-id: 86829b40dae9224088b328e7f5a16eacf8582eb5
Summary:
Refactor of all functions to compute laplacian matrices in one file.
Support for:
* Standard Laplacian
* Cotangent Laplacian
* Norm Laplacian
Reviewed By: nikhilaravi
Differential Revision: D29297466
fbshipit-source-id: b96b88915ce8ef0c2f5693ec9b179fd27b70abf9
Summary: This diff implements the inverse of D28992470 (8006842f2a): a function to extract OpenCV convention camera parameters from a PyTorch3D `PerspectiveCameras` object. This is the first part of the new PyTorch3d<>OpenCV<>Pulsar conversion functions.
Reviewed By: patricklabatut
Differential Revision: D29278411
fbshipit-source-id: 68d4555b508dbe8685d8239443f839d194cc2484
Summary: Because rotations and (rotation) quaternions live on curved manifolds, it doesn't make sense to optimize them directly. Having a prominent option to require gradient on random ones may cause people to try, and isn't particularly useful.
Reviewed By: theschnitz
Differential Revision: D29160734
fbshipit-source-id: fc9e320672349fe334747c5b214655882a460a62
Summary:
Change the cow gltf loading test to validate the texture values and not to validate the renderer output because it has an unstable pixel.
Also a couple of lints.
Reviewed By: patricklabatut
Differential Revision: D29131260
fbshipit-source-id: 5e11f066a2a638588aacb09776cc842173ef669f
Summary: As noted in #710, save_ply was failing with some values of the faces tensor. It was assuming the faces were contiguous in using view() to change them. Here we avoid doing that.
Reviewed By: patricklabatut
Differential Revision: D29159655
fbshipit-source-id: 47214a7ce915bab8d81f109c2b97cde464fd57d8
Summary: Implements a conversion function between OpenCV and PyTorch3D cameras.
Reviewed By: patricklabatut
Differential Revision: D28992470
fbshipit-source-id: dbcc9f213ec293c2f6938261c704aea09aad3c90
Summary:
Improves so3 functions to make gradient computation stable:
- Instead of `torch.acos`, uses `acos_linear_extrapolation` which has finite gradients of reasonable magnitude for all inputs.
- Adds tests for the latter.
The tests of the finiteness of the gradient in `test_so3_exp_singularity`, `test_so3_exp_singularity`, `test_so3_cos_bound` would fail if the `so3` functions would call `torch.acos` instead of `acos_linear_extrapolation`.
Reviewed By: bottler
Differential Revision: D23326429
fbshipit-source-id: dc296abf2ae3ddfb3942c8146621491a9cb740ee
Summary:
Implements a backprop-safe version of `torch.acos` that linearly extrapolates the function outside bounds.
Below is a plot of the extrapolated acos for different bounds:
{F611339485}
Reviewed By: bottler, nikhilaravi
Differential Revision: D27945714
fbshipit-source-id: fa2e2385b56d6fe534338d5192447c4a3aec540c
Summary:
Fix small face issue for point_mesh distance computation.
The issue lies in the computation of `IsInsideTriangle` which is unstable and non-symmetrical when faces with small areas are given as input. This diff fixes the issue by returning `False` for `IsInsideTriangle` when small faces are given as input.
Reviewed By: bottler
Differential Revision: D29163052
fbshipit-source-id: be297002f26b5e6eded9394fde00553a37406bee
Summary:
As reported on github, `matrix_to_quaternion` was incorrect for rotations by 180˚. We resolved the sign of the component `i` based on the sign of `i*r`, assuming `r > 0`, which is untrue if `r == 0`.
This diff handles special cases and ensures we use the non-zero elements to copy the sign from.
Reviewed By: bottler
Differential Revision: D29149465
fbshipit-source-id: cd508cc31567fc37ea3463dd7e8c8e8d5d64a235
Summary: Increase code coverage of shader and re-include them in code coverage test
Reviewed By: nikhilaravi
Differential Revision: D29097503
fbshipit-source-id: 2791989ee1562cfa193f3addea0ce72d6840614a
Summary:
There was a bug when `z_clip_value` is not None but there are no faces which are actually visible in the image due to culling. In `rasterize_meshes.py` a function `convert_clipped_rasterization_to_original_faces` is called to convert the clipped face indices etc back to the unclipped versions, but the case where there is no clipping was not handled correctly.
Fixes Github Issue #632
Reviewed By: bottler
Differential Revision: D29116150
fbshipit-source-id: fae82a0b4848c84b3ed7c7b04ef5c9848352cf5c
Summary: Fixed multiple issues with shape broadcasting in lighting, shading and blending and updated the tests.
Reviewed By: bottler
Differential Revision: D28997941
fbshipit-source-id: d3ef93f979344076b1d9098a86178b4da63844c8
Summary: Increase code coverage of subdivide_meshes and re-include it in code coverage test
Reviewed By: bottler
Differential Revision: D29097476
fbshipit-source-id: 3403ae38a90c4b53f24188eed11faae202a235b5
Summary:
When `z_clip_value = None` and faces are outside the view frustum the shape of one of the tensors in `clip.py` is incorrect.
`faces_num_clipped_verts` should be (F,) but it was (F,3). Added a new test to ensure this case is handled.
Reviewed By: bottler
Differential Revision: D29051282
fbshipit-source-id: 5f4172ba4d4a75d928404dde9abf48aef18c68bd
Summary:
When textures are set on `Meshes` we need to check if the dimensions actually match that of the verts/faces in the mesh. There was a github issue where someone tried to set the attribute after construction of the `Meshes` object and ran into an error when trying to sample textures.
The desired usage is to initialize the class with the textures (not set an attribute afterwards) but in any case we need to check the dimensions match before sampling textures.
Reviewed By: bottler
Differential Revision: D29020249
fbshipit-source-id: 9fb8a5368b83c9ec53652df92b96fc8b2613f591
Summary: Make Transform3d.to() not ignore a different dtype when device is the same and no copy is requested. Fix other methods where dtype is ignored.
Reviewed By: nikhilaravi
Differential Revision: D28981171
fbshipit-source-id: 4528e6092f4a693aecbe8131ede985fca84e84cf
Summary:
Tidy uses of `torch.device` in `Volumes`:
- Allow `str` or `torch.device` in `Volumes.to()` method
- Consistently use `torch.device` for internal type
- Fix comparison of devices
Reviewed By: nikhilaravi
Differential Revision: D28970876
fbshipit-source-id: c640cc22ced684a54cc450ac38a0f4b3435d47be
Summary:
Tidy uses of `torch.device` in `Pointclouds`:
- Allow `str` or `torch.device` in `Pointclouds.to()` method
- Consistently use `torch.device` for internal type
- Fix comparison of devices
Reviewed By: nikhilaravi
Differential Revision: D28970221
fbshipit-source-id: 3ca7104d4c0d9b20b0cff4f00e3ce931c5f1528a
Summary:
Tidy uses of `torch.device` in `Meshes`:
- Allow `str` or `torch.device` in `Meshes.to()` method
- Consistently use `torch.device` for internal type
- Fix comparison of devices
Reviewed By: nikhilaravi
Differential Revision: D28969461
fbshipit-source-id: 16d3c1f5458954bb11fdf0efea88542e94dccd7a
Summary:
Tidy uses of `torch.device` in `Transforms3d`:
- Allow `str` or `torch.device` in user-facing methods
- Consistently use `torch.device` for internal types
- Fix comparison of devices
Reviewed By: nikhilaravi
Differential Revision: D28929486
fbshipit-source-id: bd1d6cc7ede3d8fd549fd3224a9b07eec53f8164
Summary: Updated the alpha channel in the `hard_rgb_blend` function to return the mask of the pixels which have overlapping mesh faces.
Reviewed By: bottler
Differential Revision: D29001604
fbshipit-source-id: 22a2173d769f2d3ad34892d68ceb628f073bca22
Summary:
One test hits problems with CUDA 11.1 and pytorch 1.8. This seems to be a known bug, so we just run that test on the cpu in the problematic cases.
Note - the full test run is much slower with cuda 11.1 than 10.2, but this is known.
Reviewed By: patricklabatut
Differential Revision: D28938933
fbshipit-source-id: cf8ed84cd10a0b52d8f4292edbef7bd4844fea65
Summary: Restore assertNormsClose's printing of its message on failure which I broke in D26233419 (cd9786e787).
Reviewed By: nikhilaravi
Differential Revision: D28799743
fbshipit-source-id: e7a24b2558b68991c731bbd55fb3ca6c1df98f69
Summary: make assertClose print its failure information even if a message is supplied.
Reviewed By: nikhilaravi
Differential Revision: D28799745
fbshipit-source-id: 787c8c356342420cd8f40fdc0b2aba036142298e
