GitLab

Summary: Added CUDA implementation to match the new, still unused, C++ function for the core of points2vols.

Reviewed By: nikhilaravi

Differential Revision: D29548608

fbshipit-source-id: 16ebb61787fcb4c70461f9215a86ad5f97aecb4e

Summary: Single C++ function for the core of points2vols, not used anywhere yet. Added ability to control align_corners and the weight of each point, which may be useful later.

Reviewed By: nikhilaravi

Differential Revision: D29548607

fbshipit-source-id: a5cda7ec2c14836624e7dfe744c4bbb3f3d3dfe2

Summary: Statement about compatibility.

Reviewed By: nikhilaravi

Differential Revision: D30697072

fbshipit-source-id: aeb5e3e0a08c1797033d8c00b24484c8a699cb02

Summary: Fix some missing or misplaced argument descriptions.

Reviewed By: nikhilaravi

Differential Revision: D31305132

fbshipit-source-id: af4fcee9766682b2b7f7f16327e839090e377be2

Summary:
y_lengths is about `y`, not `x`.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/862

Reviewed By: bottler

Differential Revision: D31304434

Pulled By: patricklabatut

fbshipit-source-id: 1db4cd57677fc018c229e02172f95ffa903d75eb

Summary:
Changed mistake in Python f-strings causing an additional letter "f" to appear in the error messages.
The error messages would read something like :
```
raise ValueError(f"Invalid rotation matrix  shape f{matrix.shape}.")
ValueError: Invalid rotation matrix  shape ftorch.Size([4, 4]).
```
(with an additional f, probably a mistake)

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/851

Reviewed By: nikhilaravi

Differential Revision: D31238831

Pulled By: patricklabatut

fbshipit-source-id: 0ba3e61e488e467e997954278097889be606d4f8

Reviewed By: nikhilaravi

Differential Revision: D31289856

fbshipit-source-id: 5a522a69537a873bacacf2a178e5f30771aef35f

Summary: Allow saving colors as 8bit when writing .ply files.

Reviewed By: patricklabatut, nikitos9000

Differential Revision: D30905312

fbshipit-source-id: 44500982c9ed6d6ee901e04f9623e22792a0e7f7

Summary:
A note for our new algorithm for IoU of oriented 3D boxes. It includes
* A description of the algorithm
* A comparison with Objectron

Reviewed By: nikhilaravi

Differential Revision: D31288066

fbshipit-source-id: 0ea8da887bc5810bf4a3e0848223dd3590df1538

Summary: CUDA implementation of 3D bounding box overlap calculation.

Reviewed By: gkioxari

Differential Revision: D31157919

fbshipit-source-id: 5dc89805d01fef2d6779f00a33226131e39c43ed

Summary: C++ Implementation of algorithm to compute 3D bounding boxes for batches of bboxes of shape (N, 8, 3) and (M, 8, 3).

Reviewed By: gkioxari

Differential Revision: D30905190

fbshipit-source-id: 02e2cf025cd4fa3ff706ce5cf9b82c0fb5443f96

Summary:
I have implemented an exact solution for 3D IoU of oriented 3D boxes.

This file includes:
* box3d_overlap: which computes the exact IoU of box1 and box2
* box3d_overlap_sampling: which computes an approximate IoU of box1 and box2 by sampling points within the boxes

Note that both implementations currently do not support batching.

Our exact IoU implementation is based on the fact that the intersecting shape of the two 3D boxes will be formed by segments of the surface of the boxes. Our algorithm computes these segments by reasoning whether triangles of one box are within the second box and vice versa. We deal with intersecting triangles by clipping them.

Reviewed By: gkioxari

Differential Revision: D30667497

fbshipit-source-id: 2f747f410f90b7f854eeaf3036794bc3ac982917

Differential Revision: D31266959

fbshipit-source-id: 878a59ca2cfe1389e42fc338653e8d3314b56b91

Summary: Add conda builds for the newly released PyTorch version 1.9.1.

Reviewed By: patricklabatut

Differential Revision: D31140206

fbshipit-source-id: 697549a3ef0db8248f4f9b5c00cf1407296b5022

Summary:
Copy some descriptions of renderer parameters to more places so they are easier to find.

Also a couple of small corrections, and make RasterizationSettings a dataclass.

Reviewed By: nikhilaravi, patricklabatut

Differential Revision: D30899822

fbshipit-source-id: 805cf366acb7d51cb308fa574deff0657c199673

Summary: Attempt to fix #659, an observation that the rasterizer is nondeterministic, by resolving tied faces by picking those with lower index.

Reviewed By: nikhilaravi, patricklabatut

Differential Revision: D30699039

fbshipit-source-id: 39ed797eb7e9ce7370ae71259ad6b757f9449923

Summary: Unlike other cu files, sigmoid_alpha_blend uses torch/extension.h. Avoid for possible build speed win and because of a reported problem #843 on windows with CUDA 11.4.

Reviewed By: nikhilaravi

Differential Revision: D31054121

fbshipit-source-id: 53a1f985a1695a044dfd2ee1a5b0adabdf280595

Summary: Rename sample_farthest_point.cpp to not match its CUDA equivalent.

Reviewed By: nikhilaravi

Differential Revision: D31006645

fbshipit-source-id: 135b511cbde320d2b3e07fc5b027971ef9210aa9

Summary: Remove use of nonstandard C++. Noticed on windows in issue https://github.com/facebookresearch/pytorch3d/issues/843. (We use `__restrict__` in CUDA, where it is fine, even on windows)

Reviewed By: nikhilaravi

Differential Revision: D31006516

fbshipit-source-id: 929ba9b3216cb70fad3ffa3274c910618d83973f

Differential Revision: D31042748

fbshipit-source-id: fffb983bd6765d306a407587ddf64e68e57e9ecc

Summary:
CUDA implementation of farthest point sampling algorithm.

## Visual comparison

Compared to random sampling, farthest point sampling gives better coverage of the shape.

{F658631262}

## Reduction

Parallelized block reduction to find the max value at each iteration happens as follows:

1. First split the points into two equal sized parts (e.g. for a list with 8 values):
`[20, 27, 6, 8 | 11, 10, 2, 33]`
2. Use half of the thread (4 threads) to compare pairs of elements from each half (e.g elements [0, 4], [1, 5] etc) and store the result in the first half of the list:
`[20, 27, 6, 33 | 11, 10, 2, 33]`
Now we no longer care about the second part but again divide the first part into two
`[20, 27 | 6, 33| -, -, -, -]`
Now we can use 2 threads to compare the 4 elements
4. Finally we have gotten down to a single pair
`[20 | 33 | -, - | -, -, -, -]`
Use 1 thread to compare the remaining two elements
5. The max will now be at thread id = 0
`[33 | - | -, - | -, -, -, -]`
The reduction will give the farthest point for the selected batch index at this iteration.

Reviewed By: bottler, jcjohnson

Differential Revision: D30401803

fbshipit-source-id: 525bd5ae27c4b13b501812cfe62306bb003827d2

Summary: C++ implementation of iterative farthest point sampling.

Reviewed By: jcjohnson

Differential Revision: D30349887

fbshipit-source-id: d25990f857752633859fe00283e182858a870269

Summary:
This is a naive python implementation of the iterative farthest point sampling algorithm along with associated simple tests. The C++/CUDA implementations will follow in subsequent diffs.

The algorithm is used to subsample a pointcloud with better coverage of the space of the pointcloud.

The function has not been added to `__init__.py`. I will add this after the full C++/CUDA implementations.

Reviewed By: jcjohnson

Differential Revision: D30285716

fbshipit-source-id: 33f4181041fc652776406bcfd67800a6f0c3dd58

Summary: Fix issue #826. This is a correction to the joining of TexturesUV into a single scene.

Reviewed By: nikhilaravi

Differential Revision: D30767092

fbshipit-source-id: 03ba6a1d2f22e569d1b3641cd13ddbb8dcb87ec7

Summary:
* HAT_INV_SKEW_SYMMETRIC_TOL was a global variable and torch script gives an error when compiling that function. Move it to the function scope.
* torch script gives error when compiling acos_linear_extrapolation because bound is a union of tuple and float. The tuple version is kept in this diff.

Reviewed By: patricklabatut

Differential Revision: D30614916

fbshipit-source-id: 34258d200dc6a09fbf8917cac84ba8a269c00aef

Summary: In D30349234 (https://github.com/facebookresearch/pytorch3d/commit/1b8d86a104eab24ac25863c423d084d611f64bae) we introduced persistent=False to some register_buffer calls, which depend on PyTorch 1.6. We go back to the old behaviour for PyTorch 1.5.

Reviewed By: nikhilaravi

Differential Revision: D30731327

fbshipit-source-id: ab02ef98ee87440ef02479b72f4872b562ab85b5

Summary:
There has historically been a lot of duplication between the coarse rasterization logic for point clouds and meshes. This diff factors out the shared logic, so coarse rasterization of point clouds and meshes share the same core logic.

Previously the only difference between the coarse rasterization kernels for points and meshes was the logic for checking whether a {point / triangle} intersects a tile in the image. We implement a generic coarse rasterization kernel that takes a set of 2D bounding boxes rather than geometric primitives; we then implement separate kernels that compute 2D bounding boxes for points and triangles.

This change does not affect the Python API at all. It also should not change any rasterization behavior, since this diff is just a refactoring of the existing logic.

I see this diff as the first in a few pieces of rasterizer refactoring. Followup diffs should do the following:
- Add a check for bin overflow in the generic coarse rasterizer kernel: allocate a global scalar to flag bin overflow which kernel worker threads can write to in case they detect bin overflow. The C++ launcher function can then check this flag after the kernel returns and issue a warning to the user in case of overflow.
- As a slightly more involved mechanism, if bin overflow is detected then the coarse kernel can continue running in order to count how many elements fall into each bin, without actually writing out their indices to the coarse output tensor. Then the actual number of entries per bin can be used to re-allocate the output tensor and re-run the coarse rasterization kernel so that bin overflow can be automatically avoided.
- The unification of the coarse and fine rasterization kernels also allows us to insert an extra CUDA kernel prior to coarse rasterization that filters out primitives outside the view frustum. This would be helpful for rendering full scenes (e.g. Matterport data) where only a small piece of the mesh is actually visible at any one time.

Reviewed By: bottler

Differential Revision: D25710361

fbshipit-source-id: 9c9dea512cb339c42adb3c92e7733fedd586ce1b

Summary: Renaming parts of the mesh coarse rasterization and separating the bounding box calculation. All in preparation for sharing code with point rasterization.

Reviewed By: bottler

Differential Revision: D30369112

fbshipit-source-id: 3508c0b1239b355030cfa4038d5f3d6a945ebbf4

Summary: In preparation for sharing coarse rasterization between point clouds and meshes, move the functions to a new file. No code changes.

Reviewed By: bottler

Differential Revision: D30367812

fbshipit-source-id: 9e73835a26c4ac91f5c9f61ff682bc8218e36c6a

Summary: Change cyclic deps test to be independent of test discovery order. Also let it work without plotly.

Reviewed By: nikhilaravi

Differential Revision: D30669614

fbshipit-source-id: 2eadf3f8b56b6096c5466ce53b4f8ac6df27b964

Summary: Regenerate config.yml after a recent bad merge which lost a few builds.

Reviewed By: nikhilaravi

Differential Revision: D30696918

fbshipit-source-id: 3ecdfca8682baed13692ec710aa7c25dbd24dd44

Summary: Fixes GitHub issue #751. The vectorized implementation of bilinear interpolation didn't properly handle the edge cases in the same way as the `grid_sample` method in PyTorch.

Reviewed By: bottler

Differential Revision: D30684208

fbshipit-source-id: edf241ecbd72d46b94ad340a4e601e26c83db88e

Summary: Replace master with main in hard coded paths or mentions in documentation

Reviewed By: bottler

Differential Revision: D30696097

fbshipit-source-id: d5ff67bb026d90d1543d10ab027f916e8361ca69

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:
Great work! :)
Just found a link in the examples that is not working. This will fix it.

Best,
Alex

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/818

Reviewed By: nikhilaravi

Differential Revision: D30637532

Pulled By: patricklabatut

fbshipit-source-id: ed6c52375d1e760cb0fb2c0a66648dfeb0c6ed46

Summary: We won't support PyTorch 1.4 in the next release. PyTorch 1.5.0 came out in June 2020, more than a year ago.

Reviewed By: patricklabatut

Differential Revision: D30424388

fbshipit-source-id: 25499096066c9a2b909a0550394f5210409f0d74

Summary: New test that each subpackage of pytorch3d imports cleanly.

Reviewed By: patricklabatut

Differential Revision: D30001632

fbshipit-source-id: ca8dcac94491fc22f33602b3bbef481cba927094

Differential Revision: D30479084

fbshipit-source-id: 6b22dd0afe4dfb1be6249e43a56657519f11dcf1

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