GitLab

Summary:
This diff integrates the pulsar renderer source code into PyTorch3D as an alternative backend for the PyTorch3D point renderer. This diff is the first of a series of three diffs to complete that migration and focuses on the packaging and integration of the source code.

For more information about the pulsar backend, see the release notes and the paper (https://arxiv.org/abs/2004.07484). For information on how to use the backend, see the point cloud rendering notebook and the examples in the folder `docs/examples`.

Tasks addressed in the following diffs:
* Add the PyTorch3D interface,
* Add notebook examples and documentation (or adapt the existing ones to feature both interfaces).

Reviewed By: nikhilaravi

Differential Revision: D23947736

fbshipit-source-id: a5e77b53e6750334db22aefa89b4c079cda1b443

Summary:
Adds knn backward to return `grad_pts1` and `grad_pts2`. Adds `knn_gather` to return the nearest neighbors in pts2.

The BM tests include backward pass and are ran on an M40.
```
Benchmark                               Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
KNN_SQUARE_32_256_128_3_24_cpu              39558           43485             13
KNN_SQUARE_32_256_128_3_24_cuda:0            1080            1404            463
KNN_SQUARE_32_256_512_3_24_cpu              81950           85781              7
KNN_SQUARE_32_256_512_3_24_cuda:0            1519            1641            330
--------------------------------------------------------------------------------

Benchmark                               Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
KNN_RAGGED_32_256_128_3_24_cpu              13798           14650             37
KNN_RAGGED_32_256_128_3_24_cuda:0            1576            1713            318
KNN_RAGGED_32_256_512_3_24_cpu              31255           32210             16
KNN_RAGGED_32_256_512_3_24_cuda:0            2024            2162            248
--------------------------------------------------------------------------------
```

Reviewed By: jcjohnson

Differential Revision: D20945556

fbshipit-source-id: a16f616029c6b5f8c2afceb5f2bc12c5c20d2f3c

Summary: Interface and working implementation of ragged KNN. Benchmarks (which aren't ragged) haven't slowed. New benchmark shows that ragged is faster than non-ragged of the same shape.

Reviewed By: jcjohnson

Differential Revision: D20696507

fbshipit-source-id: 21b80f71343a3475c8d3ee0ce2680f92f0fae4de

Summary: Address black + isort fbsource linter warnings from D20558374 (previous diff)

Reviewed By: nikhilaravi

Differential Revision: D20558373

fbshipit-source-id: d3607de4a01fb24c0d5269634563a7914bddf1c8

Summary: Run linter after recent changes. Fix long comment in knn.h which clang-format has reflowed badly. Add crude test that code doesn't call deprecated `.type()` or `.data()`.

Reviewed By: nikhilaravi

Differential Revision: D20692935

fbshipit-source-id: 28ce0308adae79a870cb41a810b7cf8744f41ab8

Summary:
Implements K-Nearest Neighbors with C++ and CUDA versions.

KNN in CUDA is highly nontrivial. I've implemented a few different versions of the kernel, and we heuristically dispatch to different kernels based on the problem size. Some of the kernels rely on template specialization on either D or K, so we use template metaprogramming to compile specialized versions for ranges of D and K.

These kernels are up to 3x faster than our existing 1-nearest-neighbor kernels, so we should also consider swapping out `nn_points_idx` to use these kernels in the backend.

I've been working mostly on the CUDA kernels, and haven't converged on the correct Python API.

I still want to benchmark against FAISS to see how far away we are from their performance.

Reviewed By: bottler

Differential Revision: D19729286

fbshipit-source-id: 608ffbb7030c21fe4008f330522f4890f0c3c21a