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:
Support variable size pointclouds in the renderer API to allow compatibility with Pulsar rasterizer.

If radius is provided as a float, it is converted to a tensor of shape (P). Otherwise radius is expected to be an (N, P_padded) dimensional tensor where P_padded is the max number of points in the batch (following the convention from pulsar: https://our.intern.facebook.com/intern/diffusion/FBS/browse/master/fbcode/frl/gemini/pulsar/pulsar/renderer.py?commit=ee0342850210e5df441e14fd97162675c70d147c&lines=50)

Reviewed By: jcjohnson, gkioxari

Differential Revision: D21429400

fbshipit-source-id: 65de7d9cd2472b27fc29f96160c33687e88098a2

Summary:
adds `corresponding_cameras_alignment` function that estimates a similarity transformation between two sets of cameras.

The function is essential for computing camera errors in SfM pipelines.

```
Benchmark                                                   Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
CORRESPONDING_CAMERAS_ALIGNMENT_10_centers_False                32219           36211             16
CORRESPONDING_CAMERAS_ALIGNMENT_10_centers_True                 32429           36063             16
CORRESPONDING_CAMERAS_ALIGNMENT_10_extrinsics_False              5548            8782             91
CORRESPONDING_CAMERAS_ALIGNMENT_10_extrinsics_True               6153            9752             82
CORRESPONDING_CAMERAS_ALIGNMENT_100_centers_False               33344           40398             16
CORRESPONDING_CAMERAS_ALIGNMENT_100_centers_True                34528           37095             15
CORRESPONDING_CAMERAS_ALIGNMENT_100_extrinsics_False             5576            7187             90
CORRESPONDING_CAMERAS_ALIGNMENT_100_extrinsics_True              6256            9166             80
CORRESPONDING_CAMERAS_ALIGNMENT_1000_centers_False              32020           37247             16
CORRESPONDING_CAMERAS_ALIGNMENT_1000_centers_True               32776           37644             16
CORRESPONDING_CAMERAS_ALIGNMENT_1000_extrinsics_False            5336            8795             94
CORRESPONDING_CAMERAS_ALIGNMENT_1000_extrinsics_True             6266            9929             80
--------------------------------------------------------------------------------
```

Reviewed By: shapovalov

Differential Revision: D22946415

fbshipit-source-id: 8caae7ee365b304d8aa1f8133cf0dd92c35bc0dd

Summary:
Efficient PnP algorithm to fit 2D to 3D correspondences under perspective assumption.

Benchmarked both variants of nullspace and pick one; SVD takes 7 times longer in the 100K points case.

Reviewed By: davnov134, gkioxari

Differential Revision: D20095754

fbshipit-source-id: 2b4519729630e6373820880272f674829eaed073