1. 09 Apr, 2021 3 commits
  2. 08 Apr, 2021 2 commits
    • Jeremy Reizenstein's avatar
      Fix flake exceptions · 24ee2790
      Jeremy Reizenstein authored
      Summary: flake8 no longer respects the black fmt:off message, so include specific line-length exclusion.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D27624641
      
      fbshipit-source-id: adcdb6f55b382fbf252eede3f3ddeda0621da883
      24ee2790
    • David Novotny's avatar
      Implicit function docfix · 7c0d3071
      David Novotny authored
      Summary: Fixes implicit function doc.
      
      Reviewed By: theschnitz, nikhilaravi
      
      Differential Revision: D26870946
      
      fbshipit-source-id: 5d03ebbc284153c41b9d6695b28c8b4e11bc0a5c
      7c0d3071
  3. 23 Mar, 2021 1 commit
    • Jeremy Reizenstein's avatar
      CI fixes · cc08c6b2
      Jeremy Reizenstein authored
      Summary:
      Update `main` build to latest CircleCI image - Ubuntu 2020.04.
      
      Avoid torch.logical_or and logical_and for PyTorch 1.4 compatibility.
      
      Also speed up the test run with Pytorch 1.4.0 (which has no ninja) by not setting NVCC_FLAGS for it.
      
      Reviewed By: theschnitz
      
      Differential Revision: D27262327
      
      fbshipit-source-id: ddc359d134b1dc755f8b20bd3f33bb080cb3a0e1
      cc08c6b2
  4. 17 Mar, 2021 2 commits
    • Jeremy Reizenstein's avatar
      Remove _read_image from densepose example · 6c4151a8
      Jeremy Reizenstein authored
      Summary:
      As noted in #601, the example notebook was using an internal function _read_image from PyTorch3D, which has changed signature recently. It is not meant to be used externally. Switch to using PIL directly.
      
      Other changes: (1) removed unused skimage import. (2) some small tidyups. We now don't have places where cells modify values set by other cells. (3) removed bad calls to `plt.grid` which have no effect.
      
      Reviewed By: theschnitz, nikhilaravi
      
      Differential Revision: D27080372
      
      fbshipit-source-id: 2fce651b3e5d7a4619f0a2b298c5db18c8fa1e2c
      6c4151a8
    • Jeremy Reizenstein's avatar
      Tidy comments around imports · 8e1bcd55
      Jeremy Reizenstein authored
      Summary: Make black and isort stop disagreeing by removing some unneeded comments around import statements. pyre ignores are moved.
      
      Reviewed By: theschnitz
      
      Differential Revision: D27118137
      
      fbshipit-source-id: 9926d0f21142adcf9b5cfe1d394754317f6386df
      8e1bcd55
  5. 16 Mar, 2021 1 commit
    • Jeremy Reizenstein's avatar
      Plotly subsampling fix · 1b6182ba
      Jeremy Reizenstein authored
      Summary: When viewing two or more pointclouds in a single plot, we should be subsampling each one separately rather than subsampling their union.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D27010770
      
      fbshipit-source-id: 3c7e04a6049edd39756047f985d5a82c2601b3a2
      1b6182ba
  6. 11 Mar, 2021 1 commit
    • Jeremy Reizenstein's avatar
      Use old style isfinite · ff9c6612
      Jeremy Reizenstein authored
      Summary: Avoid using the newish member function isfinite. We use torch.isfinite instead for torch 1.4.0 compatibility.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D26946672
      
      fbshipit-source-id: 853c3716f40061152f1ea54a39eb60b565de7c2c
      ff9c6612
  7. 26 Feb, 2021 1 commit
    • Nikhila Ravi's avatar
      pulsar image size bug fix · 4bb3fff5
      Nikhila Ravi authored
      Summary: Small change to swap how height/width are inferred from the image_size setting.
      
      Reviewed By: gkioxari
      
      Differential Revision: D26648340
      
      fbshipit-source-id: 2c657a115c96cadf3ac63be87b0e1bfba10c9315
      4bb3fff5
  8. 25 Feb, 2021 1 commit
  9. 24 Feb, 2021 1 commit
    • Nikhila Ravi's avatar
      Bug fix for case where aspect ratio is a float · 13429640
      Nikhila Ravi authored
      Summary:
      - Fix the calculation of the non square NDC range when the H and W are not integer multiples.
      - Add test for this case
      
      Reviewed By: gkioxari
      
      Differential Revision: D26613213
      
      fbshipit-source-id: df6763cac602e9f1d516b41b432c4d2cfbaa356d
      13429640
  10. 12 Feb, 2021 1 commit
  11. 11 Feb, 2021 3 commits
    • Jeremy Reizenstein's avatar
      mesh_normal_consistency speedup · 4bfe7158
      Jeremy Reizenstein authored
      Summary: One step in finding all the pairs of vertices which share faces is a simple calculation but annoying to parallelize. It was implemented in pure Python. We move it to C++. We still pull the data to the CPU and put the answer back on the device.
      
      Reviewed By: nikhilaravi, gkioxari
      
      Differential Revision: D26073475
      
      fbshipit-source-id: ffbf4e2c347a511ab5084bceff600465812b6a52
      4bfe7158
    • Jeremy Reizenstein's avatar
      test & compilation fixes · 5ac2f421
      Jeremy Reizenstein authored
      Summary:
      Fixes mostly related to the "main" build on circleci.
      -Avoid error to do with tuple copy from initializer_list which is `explicit` on old compiler.
      -Add better reporting to copyright test.
      -Move to PackedTensorAccessor64 from the deprecated PackedTensorAccessor
      -Avoid some warnings about mismatched comparisons.
      
      The "main" build is the only one that runs the test_build stuff. In that area
      -Fix my bad copyright fix D26275931 (https://github.com/facebookresearch/pytorch3d/commit/3463f418b8a3e3c3e6b6a20007b38eb71938ec7f) / 965c9c
      -Add test that all tutorials are valid json.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D26366466
      
      fbshipit-source-id: c4ab8b7e6647987069f7cb7144aa6ab7c24bcdac
      5ac2f421
    • Shubham Goel's avatar
      bugfix in cotcurv laplacian loss. closes #551 (#553) · e13e63a8
      Shubham Goel authored
      Summary: Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/553
      
      Reviewed By: theschnitz
      
      Differential Revision: D26257591
      
      Pulled By: gkioxari
      
      fbshipit-source-id: 899a3f733a77361e8572b0900a34b55764ff08f2
      e13e63a8
  12. 09 Feb, 2021 2 commits
    • Nikhila Ravi's avatar
      update readme for v0.4 · 17468e28
      Nikhila Ravi authored
      Summary: Add link to v0.4 after it has been tagged.
      
      Reviewed By: bottler
      
      Differential Revision: D26286000
      
      fbshipit-source-id: b75893e668a18122c64aa989b6f4d150c99831be
      17468e28
    • Jeremy Reizenstein's avatar
      version number for 0.4.0 · 3c15a6c2
      Jeremy Reizenstein authored
      Summary: Update PyTorch3D version number
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D26257778
      
      fbshipit-source-id: 62a37669c51ec56d21f71b5619a1a821ae2a8e98
      3c15a6c2
  13. 08 Feb, 2021 3 commits
    • Nikhila Ravi's avatar
      CUDA/C++ Rasterizer updates to handle clipped faces · 340662e9
      Nikhila Ravi authored
      Summary:
      - Updated the C++/CUDA mesh rasterization kernels to handle the clipped faces. In particular this required careful handling of the distance calculation for faces which are cut into a quadrilateral by the image plane and then split into two sub triangles i.e. both sub triangles can't be part of the top K faces.
      - Updated `rasterize_meshes.py` to use the utils functions to clip the meshes and convert the fragments back to in terms of the unclipped mesh
      - Added end to end tests
      
      Reviewed By: jcjohnson
      
      Differential Revision: D26169685
      
      fbshipit-source-id: d64cd0d656109b965f44a35c301b7c81f451cfa0
      340662e9
    • Nikhila Ravi's avatar
      Updates to cameras and rasterizer to infer camera type correctly · 838b73d3
      Nikhila Ravi authored
      Summary: Small update to the cameras and rasterizer to correctly infer the type of camera (perspective vs orthographic).
      
      Reviewed By: jcjohnson
      
      Differential Revision: D26267225
      
      fbshipit-source-id: a58ed3bc2ab25553d2a4307c734204c1d41b5176
      838b73d3
    • Nikhila Ravi's avatar
      Utils for converting rasterization fragments of clipped meshes back to unclipped · 39f49c22
      Nikhila Ravi authored
      Summary:
      This diff adds utils functions for converting rasterization fragments of the clipped mesh into fragments expressed in terms of the original unclipped mesh.
      
      The face indices and barycentric coordinates are converted in this step. The pixel to triangle distances are handled in the rasterizer which is updated in the next diff in the stack.
      
      Reviewed By: jcjohnson
      
      Differential Revision: D26169539
      
      fbshipit-source-id: ba451d3facd60ef88a8ffaf25fd04ca07b449ceb
      39f49c22
  14. 06 Feb, 2021 1 commit
    • Nikhila Ravi's avatar
      Utils for clipping mesh faces partially behind the image plane · 23279c5f
      Nikhila Ravi authored
      Summary:
      Instead of culling faces behind the camera, partially clip them if they intersect with the image plane.
      
      This diff implements the utils functions for clipping.
      
      There are 4 cases for the mesh faces which are all handled:
      
      ```
      Case 1: the triangle is completely in front of the clipping plane (it is left
              unchanged)
      Case 2: the triangle is completely behind the clipping plane (it is culled)
      Case 3: the triangle has exactly two vertices behind the clipping plane (it is
              clipped into a smaller triangle)
      Case 4: the triangle has exactly one vertex behind the clipping plane (it is clipped
              into a smaller quadrilateral and divided into two triangular faces)
      ```
      
      Reviewed By: jcjohnson
      
      Differential Revision: D23108673
      
      fbshipit-source-id: 550a8b6a982d06065dff10aba10d47e8b144ae52
      23279c5f
  15. 05 Feb, 2021 3 commits
    • Jeremy Reizenstein's avatar
      update notebooks for s3 wheels · db6fbfad
      Jeremy Reizenstein authored
      Summary: Prepare the tutorial notebooks to use wheels from S3 when run on colab.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D26226932
      
      fbshipit-source-id: 1f9366c3fb4ba195333a5d5dfa3f6876ea934508
      db6fbfad
    • Jeremy Reizenstein's avatar
      Build wheels for s3 · e0753f0b
      Jeremy Reizenstein authored
      Summary: For Linux, instead of uploading wheels to PyPI which will only work with one particular version of PyTorch and CUDA, from the next release we will store a range of built wheels on S3.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D26209398
      
      fbshipit-source-id: 945a6907b78807e1eedb25007f87f90bbf59f80e
      e0753f0b
    • Jeremy Reizenstein's avatar
      Missing copyright · 3463f418
      Jeremy Reizenstein authored
      Summary: Fix missing copyright header in __init__.py file.
      
      Reviewed By: davnov134
      
      Differential Revision: D26275931
      
      fbshipit-source-id: 965c9cf17383aa27d35d549754ebd99ae7c25f47
      3463f418
  16. 04 Feb, 2021 1 commit
    • Jeremy Reizenstein's avatar
      Disable random-dependent tests · cd9786e7
      Jeremy Reizenstein authored
      Summary:
      These two tests fail (with non-small differences) when the seed is changed or if certain environmental changes are made. We disable them pending investigation.
      
      A small change to the tolerance at the failing assertion doesn't help. The change in common_testing helps diagnose this.
      
      Reviewed By: shapovalov
      
      Differential Revision: D26233419
      
      fbshipit-source-id: 357afc1786825256c9bade101fb15707e4dea5ed
      cd9786e7
  17. 03 Feb, 2021 1 commit
  18. 02 Feb, 2021 12 commits
    • David Novotny's avatar
      Readme · 51de308b
      David Novotny authored
      Summary: Adds the readme file.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25684459
      
      fbshipit-source-id: f1aaa621a2a67c98d5fcfe33fe9bbfea8f95b537
      51de308b
    • David Novotny's avatar
      Testing script · 2628fb56
      David Novotny authored
      Summary: Implements the test script of NeRF.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25684450
      
      fbshipit-source-id: 739169d9df706795814912bb9a15e2e65ac92df8
      2628fb56
    • David Novotny's avatar
      Generation of test camera trajectories · dc28b615
      David Novotny authored
      Summary: Implements methods for generating trajectories of test cameras.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D26100869
      
      fbshipit-source-id: cf2b61a34d4c749cd8cba881e97f6c388e57d1f8
      dc28b615
    • David Novotny's avatar
      Main training script · 9751f1f1
      David Novotny authored
      Summary: Implements the training script of NeRF.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25684439
      
      fbshipit-source-id: 8b19b6dc282eb6bf6e46ec4476bb0f13a84c90dd
      9751f1f1
    • David Novotny's avatar
      NeRF training stats logger. · 5b749118
      David Novotny authored
      Summary: Implements the `Stats` class that handles logging of the training statistics.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25684430
      
      fbshipit-source-id: 920a1c65917ab5d047988494d92173da60cfd64b
      5b749118
    • David Novotny's avatar
      NeRF dataloader. · 06668483
      David Novotny authored
      Summary: Implements the dataloader for NeRF.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25684424
      
      fbshipit-source-id: 4f7092ce23135bd418186833a087e243433babc7
      06668483
    • David Novotny's avatar
      Radiance field renderer · eb908487
      David Novotny authored
      Summary: Implements the main NeRF model class that controls the radiance field and its renderer
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25684419
      
      fbshipit-source-id: fae45572daa6748c6234bd212f3e68110f778238
      eb908487
    • David Novotny's avatar
      Implicit function · bf633ab5
      David Novotny authored
      Summary: Implements the radiance field function of NeRF
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25684413
      
      fbshipit-source-id: 4bf6dd5d22e6134a09f7b9f314536ec16670f737
      bf633ab5
    • David Novotny's avatar
      Harmonic embedding · 1e82341d
      David Novotny authored
      Summary: Implements the positional embedding of NeRF
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25684406
      
      fbshipit-source-id: 9f3b657babacff48bd6a0497d7a859607ffa5f89
      1e82341d
    • David Novotny's avatar
      NeRF Raysampler · 7cbda3ec
      David Novotny authored
      Summary: Implements the NeRF raysampler.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25684403
      
      fbshipit-source-id: 616a60f047c79479f60a6a75d214f87cbfb06d28
      7cbda3ec
    • David Novotny's avatar
      NeRF Raymarcher · fba419b7
      David Novotny authored
      Summary: An initial NeRF diff which sets up the folder structure and implements the raymarching algorithm of NeRF.
      
      Reviewed By: nikhilaravi
      
      Differential Revision: D25623990
      
      fbshipit-source-id: ac6b05a9b866358bd4bbf44858f06859d8a6ebd1
      fba419b7
    • Edgar Riba's avatar
      fixes docstring rendering in estimate_normals (#530) · f4f3d403
      Edgar Riba authored
      Summary:
      adds missing spaces in the `estimate_normals` docstrings
      
      Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/530
      
      Reviewed By: bottler
      
      Differential Revision: D26008667
      
      Pulled By: nikhilaravi
      
      fbshipit-source-id: 88cccd7e777fa2df0aea15c087db9e7fb634d93f
      f4f3d403