GitLab

Summary:
As suggested in #802. By not persisting the _xy_grid buffer, we can allow (in some cases) a model with one image_size to be loaded from a saved model which was trained at a different resolution.

Also avoid persisting _frequencies in HarmonicEmbedding for similar reasons.

BC-break: This will cause load_state_dict, in strict mode, to complain if you try to load an old model with the new code.

Reviewed By: patricklabatut

Differential Revision: D30349234

fbshipit-source-id: d6061d1e51c9f79a78d61a9f732c9a5dfadbbb47

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:
Add a CPU version to the benchmarks.

```
Benchmark                                                               Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_1000                    10100           46422             50
ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_10000                   28442           32100             18
ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_100000                 241127          254269              3
ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_1000                 54149           79480             10
ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_10000               125459          212734              4
ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_100000              512739          512739              1
ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_1000                       2866           13365            175
ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_10000                      7026           12604             72
ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_100000                    48822           55607             11
ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_1000                   38098           38576             14
ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_10000                  48006           54120             11
ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_100000                131563          138536              4
ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_1000                   64615           91735              8
ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_10000                 228815          246095              3
ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_100000               3086615         3086615              1
ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_1000               464298          465292              2
ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_10000             1053440         1053440              1
ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_100000            6736236         6736236              1
ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_1000                     11940           12440             42
ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_10000                    56641           58051              9
ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_100000                  711492          711492              1
ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_1000                 326437          329846              2
ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_10000                418514          427911              2
ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_100000              1524285         1524285              1
ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_1000                  5949           13602             85
ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_10000                 5817           13001             86
ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_100000               23833           25971             21
ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_1000               9029           16178             56
ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_10000             11595           18601             44
ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_100000            46986           47344             11
ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_1000                    2554            9747            196
ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_10000                   2676            9537            187
ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_100000                  6567           14179             77
ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_1000                 5840           12811             86
ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_10000                6102           13128             82
ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_100000              11945           11995             42
ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_1000                 7642           13671             66
ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_10000               25190           25260             20
ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_100000             212018          212134              3
ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_1000             40421           45692             13
ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_10000            92078           92132              6
ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_100000          457211          457229              2
ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_1000                   3574           10377            140
ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_10000                  7222           13023             70
ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_100000                48127           48165             11
ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_1000               34732           35295             15
ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_10000              43050           51064             12
ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_100000            106028          106058              5
--------------------------------------------------------------------------------
```

Reviewed By: patricklabatut

Differential Revision: D29522830

fbshipit-source-id: 1e857db03613b0c6afcb68a58cdd7ba032e1a874

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: Fixing recent lint problems.

Reviewed By: patricklabatut

Differential Revision: D29522647

fbshipit-source-id: 9bd89fbfa512ecd7359ec355cf12b16fb7024b47

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 (https://github.com/facebookresearch/pytorch3d/commit/8006842f2a5ab1546a90797a6394f875adce045c): 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: License lint codebase

Reviewed By: theschnitz

Differential Revision: D29001799

fbshipit-source-id: 5c59869911785b0181b1663bbf430bc8b7fb2909

Summary: Lint codebase

Reviewed By: bottler

Differential Revision: D29263057

fbshipit-source-id: ac97f01d2a79fead3b09c2cbb21b50ce688a577d

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:
Implements the SE3 logarithm and exponential maps.
(this is a second part of the split of D23326429)

Outputs of `bm_se3`:
```
Benchmark         Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
SE3_EXP_1                738             885            678
SE3_EXP_10               717             877            698
SE3_EXP_100              718             847            697
SE3_EXP_1000             729            1181            686
--------------------------------------------------------------------------------

Benchmark          Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
SE3_LOG_1               1451            2267            345
SE3_LOG_10              2185            2453            229
SE3_LOG_100             2217            2448            226
SE3_LOG_1000            2455            2599            204
--------------------------------------------------------------------------------
```

Reviewed By: patricklabatut

Differential Revision: D27852557

fbshipit-source-id: e42ccc9cfffe780e9cad24129de15624ae818472

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:
- Add MANIFEST.in and `include_package_data=True` to include dataset .json files in the installation
Fix https://github.com/facebookresearch/pytorch3d/issues/435
- Fix `load_textures=False` for ShapeNetDataset with a test
Fix https://github.com/facebookresearch/pytorch3d/issues/450, partly fix https://github.com/facebookresearch/pytorch3d/issues/444. I've set the textures to `None`, if they should be all white instead, let me know.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/593

Reviewed By: patricklabatut

Differential Revision: D29116264

Pulled By: nikhilaravi

fbshipit-source-id: 1fb0198e616b7f834dfeaf7168bb5e6e530810d1

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