364 Commits

Author SHA1 Message Date
Nikhila Ravi
103da63393 Ball Query
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
2021-08-12 14:06:32 -07:00
Pyre Bot Jr
9db70400d8 suppress errors in fbcode/vision - batch 2
Differential Revision: D30222339

fbshipit-source-id: 97d498df72ef897b8dc2405764e3ffd432082e3c
2021-08-10 10:21:59 -07:00
Nikhila Ravi
804117833e Fix to allow cameras in the renderer forward pass
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
2021-08-09 11:42:50 -07:00
Jeremy Reizenstein
4046677cf1 version 0.5.0
Summary: PyTorch3D version 0.5.0

Reviewed By: patricklabatut

Differential Revision: D29538174

fbshipit-source-id: 332516faa1d8e7bfa7c74ec3fecddc55439e2550
2021-08-03 08:10:52 -07:00
Jeremy Reizenstein
5ecce83217 PyTorch 1.4 compat
Summary: Restore compatibility with PyTorch 1.4 and 1.5, and a few lint fixes.

Reviewed By: patricklabatut

Differential Revision: D30048115

fbshipit-source-id: ee05efa7c625f6079fb06a3cc23be93e48df9433
2021-08-03 08:10:52 -07:00
CodemodService Bot
55aaec4d83 Daily arc lint --take BLACK
Reviewed By: wynsmart

Differential Revision: D30065248

fbshipit-source-id: 600915ab43d3d6d4846f60f976391f9dc1d77d10
2021-08-03 04:34:21 -07:00
Georgia Gkioxari
0c32f094af NDC/screen cameras API fix, compatibility with renderer
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
2021-08-02 01:01:10 -07:00
Patrick Labatut
9a14f54e8b Fix circular import
Summary: This fixes a recently introduced circular import: the problem went unnoticed by having `pytorch3d.renderer` imported first...

Reviewed By: bottler

Differential Revision: D29686235

fbshipit-source-id: 4b9f2faecec2cc8347ee259cfc359dc9e4f67784
2021-07-30 03:06:15 -07:00
Roman Shapovalov
e794d062e8 Improving RayBundle docstrings
Summary: This changes only documentation. We want to be explicit that ray directions are not normalised (nor assumed to be normalised) but their magnitude is used.

Reviewed By: nikhilaravi

Differential Revision: D29845210

fbshipit-source-id: b81fb3da13a42ad20e8721ed5271fd4f3d8f5acb
2021-07-23 09:33:17 -07:00
Jeremy Reizenstein
1872e0249c path_manager in obj_io
Summary: Use PathManager for checking file existence, rather than assuming the path is a local file, in a couple of cases.

Reviewed By: patricklabatut

Differential Revision: D29734621

fbshipit-source-id: e2236a7c2c50ba6916936a4d786abd601205b519
2021-07-19 05:44:20 -07:00
Jeremy Reizenstein
9e8d91ebf9 restore build tests
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
2021-07-19 05:44:20 -07:00
Alexey Sidnev
bcee361d04 Replace torch.det() with manual implementation for 3x3 matrix
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
2021-07-19 05:02:51 -07:00
Alexey Sidnev
2f668ecefe Disable gradient calculation in _check_valid_rotation_matrix()
Summary:
# Make `transform3d.py` a little bit better (performance and code quality)

## 1. Add decorator `torch.no_grad()` to the function `_check_valid_rotation_matrix()`

Function `_check_valid_rotation_matrix()` is needed to identify errors during forward pass only, it's not used for gradients.

## 2. Replace two calls `to` with the single one

Reviewed By: bottler

Differential Revision: D29656501

fbshipit-source-id: 4419e24dbf436c1b60abf77bda4376fb87a593be
2021-07-16 01:58:29 -07:00
Roman Shapovalov
0c02ae907e Adding utility methods to TensorProperties
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
2021-07-13 10:29:26 -07:00
Christoph Lassner
fa44a05567 Fixing a bug that prevents opacity gradient calculation if no other gradients are required.
Summary: An early-return test for gradient calculation did not include the opacity gradient calculation - hence would also return early without calculating gradients even if opacity gradients are required.

Reviewed By: bottler

Differential Revision: D29505684

fbshipit-source-id: 575e820b8f58b19476b2fe3288702806733e840b
2021-07-10 01:06:56 -07:00
Christoph Lassner
75432a0695 Add OpenCV camera conversion; fix bug for camera unified PyTorch3D interface.
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
2021-07-10 01:06:56 -07:00
Patrick Labatut
fef5bcd8f9 Use rotation matrices for OpenCV / PyTorch3D conversions
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
2021-07-09 10:26:34 -07:00
Pyre Bot Jr
44d2a9b623 suppress errors in vision/fair/pytorch3d
Differential Revision: D29573014

fbshipit-source-id: 87083e30d757fcceb4e380edc9973e07e6da6c76
2021-07-06 17:29:37 -07:00
David Novotny
4426a9d12c RayBundle visualization
Summary: Extends plotly_vis to visualize `RayBundle`s.

Reviewed By: patricklabatut

Differential Revision: D29014098

fbshipit-source-id: 4dee426510a1fa53d4afefbe1bcdd003684c9932
2021-07-01 17:31:01 -07:00
Jeremy Reizenstein
61754b2fac lint fixes
Summary: Fixing recent lint problems.

Reviewed By: patricklabatut

Differential Revision: D29522647

fbshipit-source-id: 9bd89fbfa512ecd7359ec355cf12b16fb7024b47
2021-07-01 16:08:40 -07:00
Patrick Labatut
5615f072d7 Add missing common module to auto-generated documentation
Summary: Add missing common module to auto-generated documentation

Reviewed By: nikhilaravi

Differential Revision: D29429687

fbshipit-source-id: fcbd02bda959b0f5674c344d17ce3f36ac4b85ae
2021-06-29 15:37:33 -07:00
Pyre Bot Jr
14f7fe4a65 suppress errors in fbcode/vision - batch 2
Differential Revision: D29458533

fbshipit-source-id: d9ef216fdbb677e49371ad91ea5e9355146c1c52
2021-06-29 09:49:16 -07:00
Jeremy Reizenstein
b8790474f1 work with old linalg
Summary: solve and lstsq have moved around in torch. Cope with both.

Reviewed By: patricklabatut

Differential Revision: D29302316

fbshipit-source-id: b34f0b923e90a357f20df359635929241eba6e74
2021-06-28 06:31:35 -07:00
Patrick Labatut
5284de6e97 Deprecate so3_exponential_map
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
2021-06-28 04:28:06 -07:00
Patrick Labatut
f593bfd3c2 More type annotations
Summary: More type annotations: device, shaders, pluggable I/O, stats in NeRF project, cameras, textures, etc...

Reviewed By: nikhilaravi

Differential Revision: D29327396

fbshipit-source-id: cdf0ceaaa010e22423088752688c8dd81f1acc3c
2021-06-25 19:56:25 -07:00
Nikhila Ravi
542e2e7c07 Save UV texture with obj mesh
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
2021-06-24 15:56:01 -07:00
Patrick Labatut
64289a491d Annotate dunder functions
Summary: Annotate the (return type of the) following dunder functions across the codebase: `__init__()`, `__len__()`, `__getitem__()`

Reviewed By: nikhilaravi

Differential Revision: D29001801

fbshipit-source-id: 928d9e1c417ffe01ab8c0445311287786e997c7c
2021-06-24 15:19:16 -07:00
Pyre Bot Jr
35855bf860 suppress errors in vision/fair/pytorch3d
Differential Revision: D29360359

fbshipit-source-id: 9e91e8499a23e30a5fc39f8f6444b2db9f6b4142
2021-06-24 05:33:55 -07:00
Georgia Gkioxari
07a5a68d50 refactor laplacian matrices
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
2021-06-24 03:53:21 -07:00
Christoph Lassner
da9974b416 Add PyTorch3D->OpenCV camera parameter conversion.
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
2021-06-23 14:38:41 -07:00
Patrick Labatut
e4039aa570 Remove _C pyre fixmes
Summary:
Get rid of pyre fixmes related to importing a native module:
- add stub file for the `_C` native extension to the internal typeshed
- add initial annotations to the new stub file
- remove the now unnecessary pyre ignores

Reviewed By: nikhilaravi

Differential Revision: D28929467

fbshipit-source-id: 6525e15c8f27215a3ff6f78392925fd0ed6ec2ac
2021-06-22 18:36:20 -07:00
Jeremy Reizenstein
279f4a154d texture map list validation
Summary: Add some more validation of a list of texture maps. Move the initialisation of maps_padded to a new function to reduce complexity.

Reviewed By: nikhilaravi

Differential Revision: D29263443

fbshipit-source-id: 153e262d2e9af21090570768020fca019e364024
2021-06-22 16:07:47 -07:00
Jeremy Reizenstein
2a0660baab Flexible #channels in TexturesUV.join_scene
Summary: The TexturesUV class supports an arbitrary number of channels. In one place in join_scene we unnecessarily assumed the usual value, 3.

Reviewed By: patricklabatut

Differential Revision: D29133477

fbshipit-source-id: de8eb15fdd55675da084634d9d99e2a3f4d35401
2021-06-22 16:07:47 -07:00
Jeremy Reizenstein
c538725885 use C for #channels in textures
Summary: Comments in textures.py were inconsistent in describing the number of channels, sometimes C, sometimes D, sometimes 3. Now always C.

Reviewed By: patricklabatut

Differential Revision: D29263435

fbshipit-source-id: 7c1260c164c52852dc9e14d0e12da4cfb64af408
2021-06-22 16:07:47 -07:00
Pyre Bot Jr
639f05a190 suppress errors in fbcode/vision - batch 2
Differential Revision: D29301375

fbshipit-source-id: a061a2fb7c7f2fd2038e31b28a5bdf0bfe1676f6
2021-06-22 12:00:22 -07:00
Patrick Labatut
af93f34834 License lint codebase
Summary: License lint codebase

Reviewed By: theschnitz

Differential Revision: D29001799

fbshipit-source-id: 5c59869911785b0181b1663bbf430bc8b7fb2909
2021-06-22 03:45:27 -07:00
Jeremy Reizenstein
ce60d4b00e remove requires_grad from random rotations
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
2021-06-21 11:45:42 -07:00
Jeremy Reizenstein
31c448a95d Test gltf texture without renderer.
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
2021-06-21 08:11:36 -07:00
Jeremy Reizenstein
354a1808ff Fix save_ply with noncontiguous faces
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
2021-06-21 06:05:45 -07:00
David Novotny
8006842f2a Conversion from OpenCV cameras
Summary: Implements a conversion function between OpenCV and PyTorch3D cameras.

Reviewed By: patricklabatut

Differential Revision: D28992470

fbshipit-source-id: dbcc9f213ec293c2f6938261c704aea09aad3c90
2021-06-21 05:03:32 -07:00
David Novotny
b2ac2655b3 SE3 exponential and logarithm maps.
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
2021-06-21 04:48:27 -07:00
David Novotny
9f14e82b5a SO3 improvements for stable gradients.
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
2021-06-21 04:48:27 -07:00
David Novotny
dd45123f20 Linearly extrapolated acos.
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
2021-06-21 04:48:27 -07:00
Georgia Gkioxari
88f5d79088 fix small face issue for ptmeshdist
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
2021-06-18 09:29:55 -07:00
Talmaj Marinc
029a9da00b Fix ShapeNetDataset (#593)
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
2021-06-18 07:02:20 -07:00
Roman Shapovalov
1b39cebe92 Sign issue about quaternion_to_matrix and matrix_to_quaternion
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
2021-06-18 06:40:02 -07:00
Patrick Labatut
a8610e9da4 Increase code coverage of shader
Summary: Increase code coverage of shader and re-include them in code coverage test

Reviewed By: nikhilaravi

Differential Revision: D29097503

fbshipit-source-id: 2791989ee1562cfa193f3addea0ce72d6840614a
2021-06-17 01:35:37 -07:00
Nikhila Ravi
c75ca04cf7 Bug fix in rendering clipped meshes
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
2021-06-15 07:51:12 -07:00
Nikhila Ravi
bc8361fa47 Lighting broadcasting bug fix
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
2021-06-14 11:48:27 -07:00
Patrick Labatut
780e231536 Increase code coverage of subdivide_meshes
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
2021-06-14 04:02:59 -07:00