GitLab

Summary: Implements 3 basic raysamplers.

Reviewed By: nikhilaravi

Differential Revision: D24110643

fbshipit-source-id: eb67d0e56773c7871ebdcb23e7e520302dc1b3c9

Summary: Implements two basic raymarchers.

Reviewed By: gkioxari

Differential Revision: D24064250

fbshipit-source-id: 18071bd039995336b7410caa403ea29fafb5c66f

Summary:
Conversion from point clouds to volumes

```
Benchmark                                                        Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
ADD_POINTS_TO_VOLUMES_10_trilinear_[25, 25, 25]_1000                 43219           44067             12
ADD_POINTS_TO_VOLUMES_10_trilinear_[25, 25, 25]_10000                43274           45313             12
ADD_POINTS_TO_VOLUMES_10_trilinear_[25, 25, 25]_100000               46281           47100             11
ADD_POINTS_TO_VOLUMES_10_trilinear_[101, 111, 121]_1000              51224           51912             10
ADD_POINTS_TO_VOLUMES_10_trilinear_[101, 111, 121]_10000             52092           54487             10
ADD_POINTS_TO_VOLUMES_10_trilinear_[101, 111, 121]_100000            59262           60514              9
ADD_POINTS_TO_VOLUMES_10_nearest_[25, 25, 25]_1000                   15998           17237             32
ADD_POINTS_TO_VOLUMES_10_nearest_[25, 25, 25]_10000                  15964           16994             32
ADD_POINTS_TO_VOLUMES_10_nearest_[25, 25, 25]_100000                 16881           19286             30
ADD_POINTS_TO_VOLUMES_10_nearest_[101, 111, 121]_1000                19150           25277             27
ADD_POINTS_TO_VOLUMES_10_nearest_[101, 111, 121]_10000               18746           19999             27
ADD_POINTS_TO_VOLUMES_10_nearest_[101, 111, 121]_100000              22321           24568             23
ADD_POINTS_TO_VOLUMES_100_trilinear_[25, 25, 25]_1000                49693           50288             11
ADD_POINTS_TO_VOLUMES_100_trilinear_[25, 25, 25]_10000               51429           52449             10
ADD_POINTS_TO_VOLUMES_100_trilinear_[25, 25, 25]_100000             237076          237377              3
ADD_POINTS_TO_VOLUMES_100_trilinear_[101, 111, 121]_1000             81875           82597              7
ADD_POINTS_TO_VOLUMES_100_trilinear_[101, 111, 121]_10000           106671          107045              5
ADD_POINTS_TO_VOLUMES_100_trilinear_[101, 111, 121]_100000          483740          484607              2
ADD_POINTS_TO_VOLUMES_100_nearest_[25, 25, 25]_1000                  16667           18143             31
ADD_POINTS_TO_VOLUMES_100_nearest_[25, 25, 25]_10000                 17682           18922             29
ADD_POINTS_TO_VOLUMES_100_nearest_[25, 25, 25]_100000                65463           67116              8
ADD_POINTS_TO_VOLUMES_100_nearest_[101, 111, 121]_1000               48058           48826             11
ADD_POINTS_TO_VOLUMES_100_nearest_[101, 111, 121]_10000              53529           53998             10
ADD_POINTS_TO_VOLUMES_100_nearest_[101, 111, 121]_100000            123684          123901              5
--------------------------------------------------------------------------------
```

Output with `DEBUG=True`
{F338561209}

Reviewed By: nikhilaravi

Differential Revision: D22017500

fbshipit-source-id: ed3e8ed13940c593841d93211623dd533974012f

Summary: Implemented a data structure for volumes.

Reviewed By: gkioxari

Differential Revision: D20342920

fbshipit-source-id: ccc23eaa183ed8a4e9cd7674b4dcf31e8a65c3c6

Summary: Implements the `__getitem__` method for `Transform3D`

Reviewed By: nikhilaravi

Differential Revision: D23813975

fbshipit-source-id: 5da752ed8ea029ad0af58bb7a7856f0995519b7a

Summary: Extends `list_to_padded`/`padded_to_list` to work for tensors with an arbitrary number of input dimensions.

Reviewed By: nikhilaravi, gkioxari

Differential Revision: D23813969

fbshipit-source-id: 52c212a2ecdb3c4dfb6ac47217715e07998f37f1

Summary:
Make no internal functions inside pytorch3d/io interpret str paths except using a PathManager from iopath which they have been given. This means we no longer use any global PathManager object and we no longer use fvcore's deprecated file_io.

To preserve the APIs, various top level functions create their own default-initialized PathManager object if they are not provided one.

Reviewed By: theschnitz

Differential Revision: D25372969

fbshipit-source-id: c176ee31439645fa54a157d6f1aef18b09501569

Summary: Allowing usort, isort and black to coexist without fighting means we can't have imports commented as deprecated from the same module as other imports.

Reviewed By: nikhilaravi

Differential Revision: D25372970

fbshipit-source-id: 637f5a0025c0df9fbec47cba73ce5387f4f8b467

Summary:
Defines a function to run marching cubes algorithm on a single or batch of 3D scalar fields. Returns a mesh's faces and vertices.

UPDATES (12/18)
- Input data is now specified as a (B, D, H, W) tensor as opposed to a (B, W, H, D) tensor. This will now be compatible with the Volumes datastructure.
- Add an option to return output vertices in local coordinates instead of world coordinates.
Also added a small fix to remove the dype for device in Transforms3D - if passing in a torch.device instead of str it causes a pyre error.

Reviewed By: jcjohnson

Differential Revision: D24599019

fbshipit-source-id: 90554a200319fed8736a12371cc349e7108aacd0

Summary: Fixes the index out of bound errors for texture sampling from a texture atlas: when barycentric coordinates are 1.0, the integer index into the (R, R) per face texture map is R (max can only be R-1).

Reviewed By: gkioxari

Differential Revision: D25543803

fbshipit-source-id: 82d0935b981352b49c1d95d5a17f9cc88bad0a82

Summary:
Similar to non square image rasterization for meshes, apply the same updates to the pointcloud rasterizer.

Main API Change:
- PointRasterizationSettings now accepts a tuple/list of (H, W) for the image size.

Reviewed By: jcjohnson

Differential Revision: D25465206

fbshipit-source-id: 7370d83c431af1b972158cecae19d82364623380

Add check for verts and faces being on same device and also checks for pointclouds/features/normals being on the same device (#384)

Summary: Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/384

Test Plan: `test_meshes` and `test_points`

Reviewed By: gkioxari

Differential Revision: D24730524

Pulled By: nikhilaravi

fbshipit-source-id: acbd35be5d9f1b13b4d56f3db14f6e8c2c0f7596

Summary: Add `return self` to the `to` function for the renderer classes.

Reviewed By: bottler

Differential Revision: D25534487

fbshipit-source-id: e8dbd35524f0bd40e835439e93184b5a1f1532ca

Summary:
There are a couple of options for supporting non square images:
1) NDC stays at [-1, 1] in both directions with the distance calculations all modified by (W/H). There are a lot of distance based calculations (e.g. triangle areas for barycentric coordinates etc) so this requires changes in many places.
2) NDC is scaled by (W/H) so the smallest side has [-1, 1]. In this case none of the distance calculations need to be updated and only the pixel to NDC calculation needs to be modified.

I decided to go with option 2 after trying option 1!

API Changes:
- Image size can now be specified optionally as a tuple

TODO:
- add a benchmark test for the non square case.

Reviewed By: jcjohnson

Differential Revision: D24404975

fbshipit-source-id: 545efb67c822d748ec35999b35762bce58db2cf4

Summary: Taubin Smoothing for filtering meshes and making them smoother. Taubin smoothing is an iterative approach.

Reviewed By: nikhilaravi

Differential Revision: D24751149

fbshipit-source-id: fb779e955f1a1f6750e704f1b4c6dfa37aebac1a

Summary: Move icp_data.pth to tests/data

Reviewed By: bottler

Differential Revision: D25012575

fbshipit-source-id: 9252d2eeca9141c82ad3bf9d3e3331a2eab5203b

Reviewed By: zertosh

Differential Revision: D24880203

fbshipit-source-id: 2034cdfc2712209e86d3d05c119c58f979b05c52

Summary: This fixes issues with `pulsar.test.TestDepth` that we are encountering on CircleCI. The ID equality test is removed, which seems to give different results on different hardware (which is okay, because the exact order of spheres can slightly vary if they're close due to numerical instabilities). The depth map validity test stays in place.

Reviewed By: bottler

Differential Revision: D24840776

fbshipit-source-id: 2f38ea4880abf202c84d2987fdd71a84c5ef3b05

Summary:
Changes to CI and some minor fixes now that pulsar is part of pytorch3d. Most significantly, add CUB to CI builds.

Make CUB_HOME override the CUB already in cudatoolkit (important for cuda11.0 which uses cub 1.9.9 which pulsar doesn't work well with.
Make imageio available for testing.
Lint fixes.
Fix some test verbosity.
Avoid use of atomicAdd_block on older GPUs.

Reviewed By: nikhilaravi, classner

Differential Revision: D24773716

fbshipit-source-id: 2428356bb2e62735f2bc0c15cbe4cff35b1b24b8

Summary: Users want to be able to obtain the depth from the renderer. Current work-around requires running the rasterizer and extra time. This change creates a new renderer class that also returns the fragments from the rasterizer.

Reviewed By: nikhilaravi

Differential Revision: D24432381

fbshipit-source-id: 6552e8a6bfee646791afb34bdb7452fbc4094aed

Summary: This commit performs pulsar example and test refinements. The examples are fully adjusted to adhere to PEP style guide and additional comments are added.

Reviewed By: nikhilaravi

Differential Revision: D24723391

fbshipit-source-id: 6d289006f080140159731e7f3a8c98b582164f1a

Summary:
This diff builds on top of the `pulsar integration` diff to provide a unified interface for the existing PyTorch3D point renderer and Pulsar. 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.

The unified interfaces are completely consistent. Switching the render backend is as easy as using `renderer = PulsarPointsRenderer(rasterizer=rasterizer).to(device)` instead of `renderer = PointsRenderer(rasterizer=rasterizer, compositor=compositor)` and adding the `gamma` parameter to the forward function. All PyTorch3D camera types are supported as far as possible; keyword arguments are properly forwarded to the camera. The `PerspectiveCamera` and `OrthographicCamera` require znear and zfar as additional parameters for the forward pass.

Reviewed By: nikhilaravi

Differential Revision: D21421443

fbshipit-source-id: 4aa0a83a419592d9a0bb5d62486a1cdea9d73ce6

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: To initialize the Cameras class currently we require the principal point, focal length and other parameters to be specified from which we calculate the intrinsic matrix. In some cases the matrix might be directly available e.g. from a dataset and the associated metadata for an image.

Reviewed By: nikhilaravi

Differential Revision: D24489509

fbshipit-source-id: 1b411f19c5f6c8074bcfbf613f3339d5e242c119

Summary: This recently added test is sensitive to the version of PIL because of different algorithms to draw ellipses/circles. Remove it as there is no obvious safe way to test this. Replace with a test for the underlying centres_for_image().

Reviewed By: theschnitz

Differential Revision: D24622465

fbshipit-source-id: e46d7384df491c71ac87ba8bbbce89507ac40080

Summary: New methods to directly plot a TexturesUV map with its used points, using PIL and matplotlib.

Reviewed By: gkioxari

Differential Revision: D23782968

fbshipit-source-id: 692970857b5be13a35a3175dc82ac03963a73555

Summary: We can represent a rotation as a vector in the axis direction, whose length is the rotation anticlockwise in radians around that axis.

Reviewed By: gkioxari

Differential Revision: D24306293

fbshipit-source-id: 2e0f138eda8329f6cceff600a6e5f17a00e4deb7

Summary:
Small fix and updated tests for multigpu rendering case.

This resolves the issue seen in: https://github.com/facebookresearch/pytorch3d/issues/401

Reviewed By: gkioxari

Differential Revision: D24314681

fbshipit-source-id: 84c5a5359844c77518b48044001daa9a86f3c43a

Summary: Issue #119. The function `sqrt(max(x, 0))` is not convex and has infinite gradient at 0, but 0 is a subgradient at 0. Here we implement it in such a way as to give 0 as the gradient.

Reviewed By: gkioxari

Differential Revision: D24306294

fbshipit-source-id: 48d136faca083babad4d64970be7ea522dbe9e09

Summary:
allow-large-files

black_any_style

Reviewed By: zertosh

Differential Revision: D24325133

fbshipit-source-id: b4afe80d1e8b2bc993f4b8e3822c02964df47462

Summary:
Fix for GitHub issue #381.

The example mesh provided in the issue only had material properties but no texture image. The current implementation of texture atlassing generated an atlas using both the material properties and the texture image but only worked if there was a texture image and associated vertex uv coordinates. I have now modified the texture atlas creation so that it doesn't require an image and can work with materials which only have material properties.

Reviewed By: gkioxari

Differential Revision: D24153068

fbshipit-source-id: 63e9d325db09a84b336b83369d5342ce588a9932

Summary: Enhance every texture type with `faces_verts_textures_packed` that allows users to query the texture of each vertex in mesh

Reviewed By: nikhilaravi

Differential Revision: D24058778

fbshipit-source-id: 19d0e3a244fa96aae462c47bf52e07dfd3b7c6f0

Summary:
Enhanced `sample_points_from_meshes` with texture sampling

* This new feature is used to return textures corresponding to the sampled points in `sample_points_from_meshes`

Reviewed By: nikhilaravi

Differential Revision: D24031525

fbshipit-source-id: 8e5d8f784cc38aa391aa8e84e54423bd9fad7ad1

Summary: Fix a few linting warnings

Reviewed By: nikhilaravi

Differential Revision: D20720810

fbshipit-source-id: c5b6a25fdd7971cc8743b54bbe162464a874071d

Summary:
Support for moving all the tensors of the renderer to another device by calling `renderer.to(new_device)`

Currently the `MeshRenderer`, `MeshRasterizer` and `SoftPhongShader` (and other shaders) are all of type `nn.Module` which already supports easily moving tensors of submodules (defined as class attributes) to a different device. However the class attributes of the rasterizer and shader (e.g. cameras, lights, materials), are of type `TensorProperties`, not nn.Module so we need to explicity create a `to` method to move these tensors to device. Note that the `TensorProperties` class already has a `to` method so we only need to call `cameras.to(device)` and don't need to worry about the internal tensors.

The other option is of course making these other classes (cameras, lights etc) also of type nn.Module.

Reviewed By: gkioxari

Differential Revision: D23885107

fbshipit-source-id: d71565c442181f739de4d797076ed5d00fb67f8e

Summary:
I'm constantly encountering 3D models with resources that have spaces in their filenames (especially on Windows) and therefore they can't be loaded in pytorch3d. Let me know what you think.

Thanks

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/358

Reviewed By: bottler

Differential Revision: D23798492

Pulled By: nikhilaravi

fbshipit-source-id: 4d85b7ee05339486d2e5ef53a531f8e6052251c5

Summary:
Make save_ply save to binary instead of ascii. An option makes the previous functionality available. save_ply's API accepts a stream, but this is undocumented; that stream must now be a binary stream not a text stream.

Avoiding warnings about making tensors from immutable numpy arrays.

Possible performance improvement when reading binary files.

Fix reading zero-length binary lists.

Reviewed By: nikhilaravi

Differential Revision: D22333118

fbshipit-source-id: b423dfd3da46e047bead200255f47a7707306811

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: Support rendering different color backgrounds for pointclouds for both compositors

Reviewed By: nikhilaravi

Differential Revision: D23611043

fbshipit-source-id: ab029650d51349340372c5bd66700e6577d48851

Summary: When the camera is vertically oriented, calculating the look_at x-axis (also known as the "right" vector) does not succeed, resulting in the x-axis being placed at the origin. Adds a check to correctly calculate the x-axis if this case occurs.

Reviewed By: nikhilaravi, sbranson

Differential Revision: D23511859

fbshipit-source-id: ee5145cdbecdbe2f7c7d288588bd0899480cb327