GitLab

Summary:
Found a bug in extending textures with vertex uv coordinates. This was due to the padded -> list conversion of vertex uv coordinates i.e.                 The number of vertices in the mesh and in verts_uvs can differ
e.g. if a vertex is shared between 3 faces, it can
have up to 3 different uv coordinates. Therefore we cannot convert directly from padded to list using _num_verts_per_mesh

Reviewed By: bottler

Differential Revision: D23233595

fbshipit-source-id: 0c66d15baae697ead0bdc384f74c27d4c6539fc9

Summary:
- Added sbranson's fit mesh tutorial to the website
- Updated rendering docs with info about texturing and new shader types.

TODO:
- add pointcloud rendering tutorial to the website as well (https://github.com/facebookresearch/pytorch3d/blob/master/docs/tutorials/render_colored_points.ipynb)
- docs for camera
- update some tutorials which depended on the Textures from structures.

Reviewed By: gkioxari

Differential Revision: D23143977

fbshipit-source-id: 6843c9bf3ce11115c459c64da5b0ad778dc92177

Summary:
faces_uvs_packed and verts_uvs_packed were only used in one place and the definition of the former was ambiguous. This meant that the wrong coordinates could be used for meshes other than the first in the batch. I have therefore removed both functions and build their common result inline. Added a test that a simple batch of two meshes is rendered consistently with the rendering of each alone. This test would have failed before.

I hope this fixes https://github.com/facebookresearch/pytorch3d/issues/283.

Some other small improvements to the textures code.

Reviewed By: nikhilaravi

Differential Revision: D23161936

fbshipit-source-id: f99b560a46f6b30262e07028b049812bc04350a7

Summary: A triangle is culled if any vertex in a triangle is behind the camera.  This fixes incorrect rendering of triangles that are partially behind the camera, where screen coordinate calculations are strange.  It doesn't work for triangles that are partially behind the camera but still intersect with the view frustum.

Reviewed By: nikhilaravi

Differential Revision: D22856181

fbshipit-source-id: a9cbaa1327d89601b83d0dfd3e4a04f934a4a213

Summary:
Refactor cameras
* CamerasBase was enhanced with `transform_points_screen` that transforms projected points from NDC to screen space
* OpenGLPerspective, OpenGLOrthographic -> FoVPerspective, FoVOrthographic
* SfMPerspective, SfMOrthographic -> Perspective, Orthographic
* PerspectiveCamera can optionally be constructred with screen space parameters
* Note on Cameras and coordinate systems was added

Reviewed By: nikhilaravi

Differential Revision: D23168525

fbshipit-source-id: dd138e2b2cc7e0e0d9f34c45b8251c01266a2063

Summary: Tutorial for ShapeNetCore & R2N2.

Reviewed By: gkioxari

Differential Revision: D22916882

fbshipit-source-id: 752742be87f44919164ec7eafcc9c09c17a0f8a3

Summary:
Because of the way Sphinx was parsing this link in Markdown, the link wasn't working properly. This should fix it.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/330

Test Plan: Tested via local Sphinx.

Reviewed By: nikhilaravi

Differential Revision: D23244163

Pulled By: atroyn

fbshipit-source-id: 019712a841d76391a5210dcd98c77a822947204a

Differential Revision: D23180198

fbshipit-source-id: cad1fa7ba9935f3ca20410a2575e173999c04be1

Summary: Add `detach` for Meshes, Pointclouds, Textures

Reviewed By: nikhilaravi

Differential Revision: D23070418

fbshipit-source-id: 68671124ce114c4495d7ef3c944c9aac3d0db2d8

Summary:
Small fix to the softmax blending function.

To avoid overflow in the exponential for the softmax, the exponent is shifted by the maximum value. In the final calculation of the color there is a weighted sum between the pixel color and the background color - in order for the sum to be correct, the background color also needs to be handled in the same way witt the shifted exponent.

Reviewed By: gkioxari

Differential Revision: D23148301

fbshipit-source-id: 86066586ee7d3ce7bd4a2076b12ce191fbd151a7

Summary: documentation for datasets

Reviewed By: bottler, gkioxari

Differential Revision: D22992266

fbshipit-source-id: 44aaa8227af04c1baa5ea6c31ba131dea2b9675b

Summary: Continue extracting reusable I/O functions to a separate utils module (and remove duplication).

Reviewed By: nikhilaravi

Differential Revision: D20720433

fbshipit-source-id: e82b19560a5dc8a506c4c4d098da69c202790c4f

Summary: Return R2N2's voxel coordinates.

Reviewed By: nikhilaravi

Differential Revision: D22462530

fbshipit-source-id: a995cfa0957b2561eb3b0f4591cb1db42170bc68

Summary: Return rotation, translation and intrinsic matrices necessary to reproduce R2N2's own renderings.

Reviewed By: nikhilaravi

Differential Revision: D22462520

fbshipit-source-id: 46a3859743ebc43c7a24f75827d2be3adf3f486b

Summary: Latest pytorch doesn't support cuda 10.0 and now its pytorch/conda-cuda docker image doesn't include it either. Here we remove the pytorch3d builds which use cuda 10.0.

Reviewed By: nikhilaravi

Differential Revision: D22999392

fbshipit-source-id: c834477fc7c812c2d0594dccd9e9471e33a4ec5e

Summary: The recently added part of a test was assuming that the random gpu was gpu 0.

Reviewed By: nikhilaravi

Differential Revision: D22948397

fbshipit-source-id: 88107e19fc3118e763f95be43a614941176a08f9

Summary: CPU implementation of the graph convolution op.

Reviewed By: nikhilaravi, gkioxari

Differential Revision: D21384361

fbshipit-source-id: bc96730e9727bb9aa1b0a232dcb82f0c0d12fe6b

Summary:
The main pytorch wheels on PyPI support CUDA 10.2. Here we make pytorch3d's wheels do the same, instead of being cpu only. This should ultimately make life easier in colab.

Also a little script to count builds, which can be useful for nightly jobs.

Reviewed By: gkioxari

Differential Revision: D22924321

fbshipit-source-id: d6cea9bfbab49bcb0080f65608066c553ea8bb4d

Differential Revision: D22834017

fbshipit-source-id: 441124c67a2bbfe086e2983d5c4c845b58fc965c

Summary:
A fairly big refactor of the texturing API with some breaking changes to how textures are defined.

Main changes:
- There are now 3 types of texture classes: `TexturesUV`, `TexturesAtlas` and `TexturesVertex`. Each class:
   - has a `sample_textures` function which accepts the `fragments` from rasterization and returns `texels`. This means that the shaders will not need to know the type of the mesh texture which will resolve several issues people were reporting on GitHub.
  -  has a `join_batch` method for joining multiple textures of the same type into a batch

Reviewed By: gkioxari

Differential Revision: D21067427

fbshipit-source-id: 4b346500a60181e72fdd1b0dd89b5505c7a33926

Summary: Reduce the size of the data in this test, so that on circleci it doesn't run out of memory when pytorch (1.6) is used.

Reviewed By: gkioxari

Differential Revision: D22801490

fbshipit-source-id: 9591253c3d47430facd769a2c51a0b1722e0a305

Summary: Remove composite params from tutorial

Reviewed By: nikhilaravi

Differential Revision: D22809242

fbshipit-source-id: e5ed4e93fc892baf74e3a464119f0d11973423c3

Summary: Make CI builds with pytorch 1.6.

Reviewed By: gkioxari

Differential Revision: D22790325

fbshipit-source-id: 5b0e075f952de9df2de03b65c16fd69140ab6fdd

Summary: Tutorial showing how to create a synthetic dataset by rendering a cow from multiple views, fit a mesh using a differential silhouette renderer, then fit a mesh using an RGB renderer.

Reviewed By: nikhilaravi

Differential Revision: D22513859

fbshipit-source-id: 24bdaac4ebec6dd01f98e2f5c702065f9335ff33

Summary: Adding BlenderCamera (for rendering with R2N2 Blender transformations in the next diff).

Reviewed By: nikhilaravi

Differential Revision: D22462515

fbshipit-source-id: 4b40ee9bba8b6d56788dd3c723036ec704668153

Summary:
Sample/Get all views at the loading phase instead of returning phase;
Load only views from the split instead of all 24 views;
Test the numbers of views loaded are correct for each category.

Reviewed By: nikhilaravi

Differential Revision: D22631414

fbshipit-source-id: 1c5ce99fe2bdf6618c1aa0b69bb6899473376bc2

Reviewed By: pradeep90

Differential Revision: D22628883

fbshipit-source-id: a19c271b4025c0e3c61408604a7e0f9fbcbdfa5b

Summary: Github does not support embedding youtube videos! Changing it to a link with a thumbnail.

Reviewed By: gkioxari

Differential Revision: D22601430

fbshipit-source-id: 1087657bc379a228a33eced1bee8492cef8373a7

Summary: Fixing several unused imports and pyre/linter warnings.

Reviewed By: bottler

Differential Revision: D22592491

fbshipit-source-id: 463383b9b73a545949475044fb5c531712f8482c

Summary: Added link to the youtube video of the PyTorch hackathon tutorial to the README.

Reviewed By: bottler

Differential Revision: D22592655

fbshipit-source-id: 7b3791042a0d6f7e1d3b5602580f10b08a48fe43

Summary:
1. CircleCI tests fail because of different randomisation. I was able to reproduce it on devfair (with an older version of pytorch3d though), but with a new threshold, it works. Let’s push and see if it will work in CircleCI.
2. Fixing linter’s issue with `l` variable name.

Reviewed By: bottler

Differential Revision: D22573244

fbshipit-source-id: 32cebc8981883a3411ed971eb4a617469376964d

Summary:
Added support for barycentric clipping in the C++/CUDA rasterization kernels which can be switched on/off via a rasterization setting.

Added tests and a benchmark to compare with the current implementation in PyTorch - for some cases of large image size/faces per pixel the cuda version is 10x faster.

Reviewed By: gkioxari

Differential Revision: D21705503

fbshipit-source-id: e835c0f927f1e5088ca89020aef5ff27ac3a8769

Summary:
C++/CUDA implementation of forward and backward passes for the sigmoid alpha blending function.

This is slightly faster than the vectorized implementation in Python, but more importantly uses less memory due to fewer tensors being created.

Reviewed By: gkioxari

Differential Revision: D19980671

fbshipit-source-id: 0779055d2c68b1f20fb0870e60046077ef4613ff

Summary: R2N2 returns R2N2's own renderings of ShapeNetCore models.

Reviewed By: nikhilaravi

Differential Revision: D22266988

fbshipit-source-id: 36e67bd06c6459773e6e5f654259166b579be36a

Summary: Adding a render function for R2N2.

Reviewed By: nikhilaravi

Differential Revision: D22230228

fbshipit-source-id: a9f588ddcba15bb5d8be1401f68d730e810b4251

Summary: Skeleton of R2N2 that for now only returns verts and faces extracted from ShapeNetCore v1.

Reviewed By: nikhilaravi

Differential Revision: D22203656

fbshipit-source-id: 00db6ac76bfdb76fdbc77a2087c34a3f0ff01e6a

Summary: Adding collate_batched_meshes for datasets.utils: takes in a list of dictionaries and merge them into one dictionary (while adding a merged mesh to the dictionary).

Reviewed By: nikhilaravi

Differential Revision: D22180404

fbshipit-source-id: f811f9a140f09638f355ad5739bffa6ee415819f

Summary: Additional functionality for renderer in ShapeNetCore: users can select which objects to render by specifying their model_ids, or users could choose to render several random objects in some categories, or users could specify indices of the objects in the loaded dataset. (currently doesn't support changing lighting, still investigating why lighting is causing instability in renderings)

Reviewed By: nikhilaravi

Differential Revision: D22179594

fbshipit-source-id: 74c49094ffa3ea2eb71de9451f9e5da5053d356d

Summary: Adding a renderer to ShapeNetCore (Note that the lights are currently turned off for the test; will investigate why lighting causes instability in rendering)

Reviewed By: nikhilaravi

Differential Revision: D22102673

fbshipit-source-id: a704756a1e93b61d5a879f0e5ee14ebcb0df49d7

Differential Revision: D22519468

fbshipit-source-id: 6e39c2e50ef95f37df407dbc6d186cc97832fc7d