1. 13 Feb, 2024 1 commit
    • Jeremy Reizenstein's avatar
      Make OpenGL optional in tests · 8772fe0d
      Jeremy Reizenstein authored
      Summary: Add an option to run tests without the OpenGL Renderer.
      
      Reviewed By: patricklabatut
      
      Differential Revision: D53573400
      
      fbshipit-source-id: 54a14e7b2f156d24e0c561fdb279f4a9af01b793
      8772fe0d
  2. 08 Feb, 2024 1 commit
    • Ada Martin's avatar
      c++ marching cubes fix · c292c71c
      Ada Martin authored
      Summary:
      Fixes https://github.com/facebookresearch/pytorch3d/issues/1641. The bug was caused by the mistaken downcasting of an int64_t into int, causing issues only on inputs large enough to have hashes that escaped the bounds of an int32.
      
      Also added a test case for this issue.
      
      Reviewed By: bottler
      
      Differential Revision: D53505370
      
      fbshipit-source-id: 0fdd0efc6d259cc3b0263e7ff3a4ab2c648ec521
      c292c71c
  3. 07 Feb, 2024 1 commit
  4. 31 Jan, 2024 1 commit
  5. 27 Jan, 2024 1 commit
  6. 26 Jan, 2024 1 commit
  7. 25 Jan, 2024 1 commit
  8. 18 Jan, 2024 1 commit
    • Dimitris Prountzos's avatar
      Fix compiler warning in knn.ku · 1e817914
      Dimitris Prountzos authored
      Summary: This change updates the type of p2_idx from size_t to int64_t to address compiler warnings related to signed/unsigned comparison.
      
      Reviewed By: bottler
      
      Differential Revision: D52879393
      
      fbshipit-source-id: de5484d78a907fccdaae3ce036b5e4a1a0a4de70
      1e817914
  9. 16 Jan, 2024 1 commit
  10. 04 Jan, 2024 1 commit
    • Abdelrahman Selim's avatar
      Update so3 operations for numerical stability · 292acc71
      Abdelrahman Selim authored
      Summary: Replace implementations of `so3_exp_map` and `so3_log_map` in so3.py with existing more-stable implementations.
      
      Reviewed By: bottler
      
      Differential Revision: D52513319
      
      fbshipit-source-id: fbfc039643fef284d8baa11bab61651964077afe
      292acc71
  11. 03 Jan, 2024 1 commit
  12. 21 Dec, 2023 2 commits
  13. 19 Dec, 2023 1 commit
    • Hassan Lotfi's avatar
      Submeshing TexturesUV · 8a27590c
      Hassan Lotfi authored
      Summary: Implement `submeshes` for TexturesUV. Fix what Meshes.submeshes passes to the texture's submeshes function to make this possible.
      
      Reviewed By: bottler
      
      Differential Revision: D52192060
      
      fbshipit-source-id: 526734962e3376aaf75654200164cdcebfff6997
      8a27590c
  14. 11 Dec, 2023 1 commit
    • Eric Young's avatar
      PyTorch3D - Avoid flip in TexturesAtlas · 06cdc313
      Eric Young authored
      Summary: Performance improvement: Use torch.lerp to map uv coordinates to the range needed for grid_sample (i.e. map [0, 1] to [-1, 1] and invert the y-axis)
      
      Reviewed By: bottler
      
      Differential Revision: D51961728
      
      fbshipit-source-id: db19a5e3f482e9af7b96b20f88a1e5d0076dac43
      06cdc313
  15. 07 Dec, 2023 2 commits
  16. 05 Dec, 2023 3 commits
  17. 04 Dec, 2023 1 commit
    • Jeremy Reizenstein's avatar
      lint · 83bacda8
      Jeremy Reizenstein authored
      Summary: Fix recent flake complaints
      
      Reviewed By: MichaelRamamonjisoa
      
      Differential Revision: D51811912
      
      fbshipit-source-id: 65183f5bc7058da910e4d5a63b2250ce8637f1cc
      83bacda8
  18. 29 Nov, 2023 1 commit
  19. 16 Nov, 2023 1 commit
  20. 14 Nov, 2023 4 commits
  21. 31 Oct, 2023 2 commits
    • Jeremy Reizenstein's avatar
      version 0.7.5 · 2f11ddc5
      Jeremy Reizenstein authored
      Summary: update
      
      Reviewed By: MichaelRamamonjisoa
      
      Differential Revision: D50806966
      
      fbshipit-source-id: 95fd341c9e5e4e07b689eb71b3a729baff3b8192
      2f11ddc5
    • Jeremy Reizenstein's avatar
      update notebooks for 0.7.5 · 650cc09d
      Jeremy Reizenstein authored
      Summary:
      ```
      sed -i 's/startswith((\"1.13.\", \"2.0.\"))/startswith\(\"2.1.\"\)/' *b
      ```
      
      Reviewed By: shapovalov
      
      Differential Revision: D50806967
      
      fbshipit-source-id: df19462564edb1f840753efeae96b516c7a9f764
      650cc09d
  22. 30 Oct, 2023 3 commits
    • Jeremy Reizenstein's avatar
      fix warning from cross · 8c15afe7
      Jeremy Reizenstein authored
      Summary: Don't call tensor.cross() without dim, to avoid new warning.
      
      Reviewed By: MichaelRamamonjisoa
      
      Differential Revision: D49879590
      
      fbshipit-source-id: e9ba83923b6dc3bcface6782b8b26729ab5b0a4c
      8c15afe7
    • Jeremy Reizenstein's avatar
      CI fixes (#1676) · 6b437e21
      Jeremy Reizenstein authored
      Summary:
      Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1676
      
      Remove CUDA 10.2 build, remove sm35 from cuda12.
      
      Reviewed By: MichaelRamamonjisoa
      
      Differential Revision: D50790929
      
      fbshipit-source-id: 2b8cd34493b633a97b4066e0fd61aff077f7ce0c
      6b437e21
    • Jeremy Reizenstein's avatar
      missing cudaGetLastError · 03f17ca1
      Jeremy Reizenstein authored
      Summary: Investigating a reported problem.
      
      Reviewed By: MichaelRamamonjisoa
      
      Differential Revision: D50791296
      
      fbshipit-source-id: 8dc162b87d02debf05d16c2b4816fcd57234d7e0
      03f17ca1
  23. 17 Oct, 2023 2 commits
  24. 22 Sep, 2023 1 commit
  25. 20 Sep, 2023 1 commit
  26. 05 Sep, 2023 1 commit
  27. 26 Aug, 2023 1 commit
  28. 15 Aug, 2023 1 commit
    • Haritha Jayasinghe's avatar
      add None option for chamfer distance point reduction (#1605) · d84f274a
      Haritha Jayasinghe authored
      Summary:
      The `chamfer_distance` function currently allows `"sum"` or `"mean"` reduction, but does not support returning unreduced (per-point) loss terms. Unreduced losses could be useful if the user wishes to inspect individual losses, or perform additional modifications to loss terms before reduction. One example would be implementing a robust kernel over the loss.
      
      This PR adds a `None` option to the `point_reduction` parameter, similar to `batch_reduction`. In case of bi-directional chamfer loss, both the forward and backward distances are returned (a tuple of Tensors of shape `[D, N]` is returned). If normals are provided, similar logic applies to normals as well.
      
      This PR addresses issue https://github.com/facebookresearch/pytorch3d/issues/622.
      
      Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1605
      
      Reviewed By: jcjohnson
      
      Differential Revision: D48313857
      
      Pulled By: bottler
      
      fbshipit-source-id: 35c824827a143649b04166c4817449e1341b7fd9
      d84f274a
  29. 20 Jul, 2023 1 commit