GitLab

Summary: Added missing include for cstdint for Windows and removed problematic inline assembly.

Reviewed By: bottler

Differential Revision: D24838053

fbshipit-source-id: 95496be841c2c22a82068073d4740e98ee8a02ac

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: Move to a local import for calculating pointcloud normals, similar to _compute_face_areas_normals on Meshes.

Reviewed By: theschnitz

Differential Revision: D24695260

fbshipit-source-id: 9e1eb5d15017975b8c4f4175690cc3654f38d9a4

Summary: This diff updates the documentation and tutorials with information about the new pulsar backend. 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.

Reviewed By: nikhilaravi

Differential Revision: D24498129

fbshipit-source-id: e312b0169a72b13590df6e4db36bfe6190d742f9

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 avoid docker's new ratelimiting, we sign in.

Reviewed By: theschnitz

Differential Revision: D24681688

fbshipit-source-id: 6bb1a86ee15a151758e8a2bdb081da280308ad0c

Summary:
Updated the README with:
- Contributor list
- News updates
- New tutorial links

Reviewed By: gkioxari

Differential Revision: D24412028

fbshipit-source-id: 0c4ba9ebe16a7a4728801356a9271ff152282686

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: CircleCI build configuration to support pytorch1.7, including binaries with cuda 11.0. Note that the default torch on pip is still on cuda 10.2, so I have left the `main` (non conda build) on cuda 10.2 with the existing driver.

Reviewed By: gkioxari

Differential Revision: D24623523

fbshipit-source-id: 59cfa1be06c16225f0f12ed336c07220e8a9a511

Summary: We envision `pytorch3d.vis` to contain submodules with different dependencies. Allow (and require) them to be imported independently.

Reviewed By: theschnitz

Differential Revision: D24622519

fbshipit-source-id: 44840f70f5fd2bd410405bf09546024e48238744

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: Script to execute tutorials inside docker with the nightly build.

Reviewed By: nikhilaravi

Differential Revision: D24503200

fbshipit-source-id: cfa010a7750627d4e87d224a112ff77952feeb55

Summary: We were importing torch, torchvision, PyTorch3D, and sys twice. This is just removing the duplicate (unneeded) imports

Reviewed By: theschnitz

Differential Revision: D24479270

fbshipit-source-id: 1048732f65242eb776c3eef537cb1ae58815c1eb

Summary: Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/409

Reviewed By: bottler

Differential Revision: D24478451

Pulled By: nikhilaravi

fbshipit-source-id: 933d6f7a02a3118ee30ecda045fd9f62a7df1176

Summary:
The README for the project refers to the BSD 3-Clause License, but the License file has only BSD License as the name. Updated the License name to BSD 3-Clause License for correct reference.

License files are an important part of source code and should not have errors. This helps developers to correctly reference the license when integrating the source code within their applications.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/310

Reviewed By: theschnitz

Differential Revision: D24220599

Pulled By: nikhilaravi

fbshipit-source-id: 657bde0abe946e95864fc048eb930a91ddf08b99

Summary: Fix axis_angle conversions where I used torch.square which doesn't work with pytorch 1.4

Reviewed By: nikhilaravi

Differential Revision: D24451546

fbshipit-source-id: ba26f7dad5fa991f0a8f7d3d09ee7151163aecf4

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: Take in a renderer with camera(s) and render the cameras as wireframes in the corresponding plotly plots

Reviewed By: nikhilaravi

Differential Revision: D24151706

fbshipit-source-id: f8e86d61f3d991500bafc0533738c79b96bda630

Summary:
Use a provided renderer's camera positions to render a plotly plot to match what the renderer would render for pointclouds and meshes.
- takes in a Cameras object for viewpoints
- for each subplot, will index into the Cameras object (or use the Cameras object, if len(viewpoint_cameras) == 1 and use the Cameras' eye and at vectors to set plotly's camera's corresponding values, the eye and center values.

Reviewed By: nikhilaravi

Differential Revision: D24094934

fbshipit-source-id: 48abcdb04c6909a172ba9f721522c3446952a089

Summary: Change the two affected tutorials to use plot_scene and plot_batch_individually.

Reviewed By: nikhilaravi

Differential Revision: D24235480

fbshipit-source-id: ca9d73bfb7ccf733efaf16299c15927406d7f2aa

Summary:
- adds plot_batch_individually
- for each batched object, plots each object in its own subplot with other same-indexed elements of the other batched objects provided as input

Reviewed By: nikhilaravi

Differential Revision: D24258389

fbshipit-source-id: a80128e6e7a03a44c257b0598569159afadb2d39

Summary: Defines a function plot_scene that takes in a dictionary defining subplot and trace layouts for Mesh/Pointcloud objects and plots them. Also supports other plotly axis arguments and mesh lighting. Plot_batch_individually is a wrapper function that takes in one or multiple batched Meshes/Pointclouds and uses plot_scene to plot each element within a batch in an individual subplot, possibly sharing that subplot with traces of other individual elements of the other batched structures passed in.

Reviewed By: nikhilaravi

Differential Revision: D24235479

fbshipit-source-id: 9f669f1b186d55fe5c75552083316c0cf1387472

Summary:
As pointed out in #328, we had an indexing operation where a reshape would do and be faster. The resulting faces_packed_to_edges_packed is no longer contiguous.

Also fix a use of faces_packed_to_edges_packed which might modify the object unintentionally.

Reviewed By: theschnitz

Differential Revision: D24390292

fbshipit-source-id: 225677d8fcc1d6b76efad7706718ecdb5182ffe1

Summary: Added images for four tutorials to add to the README.

Reviewed By: gkioxari

Differential Revision: D24411993

fbshipit-source-id: 5f0b2256efb156b5956013c26b8ddb1631bd1c46

Summary: The linter has become stricter about the indenting of comments and docstrings. This was accompanied by a codemod. In a few places we can fix the problem nicer than the codemod has.

Reviewed By: gkioxari

Differential Revision: D24363880

fbshipit-source-id: 4cff3bbe3d2a834bc92a490469a2b24fa376e6ab

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: Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/386

Reviewed By: gkioxari

Differential Revision: D24220501

Pulled By: nikhilaravi

fbshipit-source-id: 5bb0014b46a89fde52c9aaccba0e3ba6d485430f

Summary: As mentioned in a comment on https://github.com/facebookresearch/pytorch3d/issues/77, we can't use this function in Python 3.6. It's easy to write our own version.

Reviewed By: gkioxari

Differential Revision: D24249915

fbshipit-source-id: 4c70a3efb03daa115041d082e616511297eab8fa

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: Importing from pytorch3d.visualization is wordy, so shortened the path to the vis module and updated the relevant imports.

Reviewed By: nikhilaravi

Differential Revision: D24116527

fbshipit-source-id: e0e4da7d48c5afedec07482d7be43362b6822445

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: Add markdown note explaining why PyTorch3D has plotly visualizations, examples, and how to save these visualizations as an image.

Reviewed By: nikhilaravi

Differential Revision: D23976283

fbshipit-source-id: cbbaffd1f0ebe3466841e42fdb454d85773152cd

Summary: Add examples of using the Plotly visualization functions to the corresponding tutorial notebooks.

Reviewed By: nikhilaravi

Differential Revision: D23879109

fbshipit-source-id: ea8c45aa6c828eb2f6ea2ae1c8846adc486f92e0

Summary:
Visualize a pointcloud in plotly.
- customize lighting and light position
- customizable axis arguments
- customizable height and width of plotly figure
- render batches in subplots or the same plot

Reviewed By: nikhilaravi

Differential Revision: D23872391

fbshipit-source-id: 9b1e1fd417500521be9d0eb85d71c77a538fa77c