Skip to content
GitLab
切换分支/标签
  1. 04 1月, 2024 1 次提交
    • Abdelrahman Selim's avatar
      Update so3 operations for numerical stability · 292acc71
      由 Abdelrahman Selim 创作于 
      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
  3. 03 1月, 2024 1 次提交
  5. 21 12月, 2023 2 次提交
  7. 19 12月, 2023 1 次提交
    • Hassan Lotfi's avatar
      Submeshing TexturesUV · 8a27590c
      由 Hassan Lotfi 创作于 
      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
  9. 11 12月, 2023 1 次提交
    • Eric Young's avatar
      PyTorch3D - Avoid flip in TexturesAtlas · 06cdc313
      由 Eric Young 创作于 
      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
  11. 07 12月, 2023 2 次提交
  13. 05 12月, 2023 3 次提交
  15. 04 12月, 2023 1 次提交
    • Jeremy Reizenstein's avatar
      lint · 83bacda8
      由 Jeremy Reizenstein 创作于 
      Summary: Fix recent flake complaints

Reviewed By: MichaelRamamonjisoa

Differential Revision: D51811912

fbshipit-source-id: 65183f5bc7058da910e4d5a63b2250ce8637f1cc
      83bacda8
  17. 29 11月, 2023 1 次提交
  19. 16 11月, 2023 1 次提交
  21. 14 11月, 2023 4 次提交
  23. 31 10月, 2023 2 次提交
    • Jeremy Reizenstein's avatar
      version 0.7.5 · 2f11ddc5
      由 Jeremy Reizenstein 创作于 
      Summary: update

Reviewed By: MichaelRamamonjisoa

Differential Revision: D50806966

fbshipit-source-id: 95fd341c9e5e4e07b689eb71b3a729baff3b8192
      2f11ddc5
    • Jeremy Reizenstein's avatar
      update notebooks for 0.7.5 · 650cc09d
      由 Jeremy Reizenstein 创作于 
      Summary:
```
sed -i 's/startswith((\"1.13.\", \"2.0.\"))/startswith\(\"2.1.\"\)/' *b
```

Reviewed By: shapovalov

Differential Revision: D50806967

fbshipit-source-id: df19462564edb1f840753efeae96b516c7a9f764
      650cc09d
  25. 30 10月, 2023 3 次提交
    • Jeremy Reizenstein's avatar
      fix warning from cross · 8c15afe7
      由 Jeremy Reizenstein 创作于 
      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
      由 Jeremy Reizenstein 创作于 
      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
      由 Jeremy Reizenstein 创作于 
      Summary: Investigating a reported problem.

Reviewed By: MichaelRamamonjisoa

Differential Revision: D50791296

fbshipit-source-id: 8dc162b87d02debf05d16c2b4816fcd57234d7e0
      03f17ca1
  27. 17 10月, 2023 2 次提交
  29. 22 9月, 2023 1 次提交
  31. 20 9月, 2023 1 次提交
  33. 05 9月, 2023 1 次提交
  35. 26 8月, 2023 1 次提交
  37. 15 8月, 2023 1 次提交
    • Haritha Jayasinghe's avatar
      add None option for chamfer distance point reduction (#1605) · d84f274a
      由 Haritha Jayasinghe 创作于 
      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
  39. 20 7月, 2023 1 次提交
  41. 14 7月, 2023 2 次提交
    • Jeremy Reizenstein's avatar
      attempt to fix readthedocs · 57f6e792
      由 Jeremy Reizenstein 创作于 
      Summary:
Something's wrong with recommonmark/CommonMark/six, let's see if this fixes it.

https://readthedocs.org/projects/pytorch3d/builds/21292632/

```
  File "/home/docs/checkouts/readthedocs.org/user_builds/pytorch3d/envs/latest/lib/python3.11/site-packages/sphinx/config.py", line 368, in eval_config_file
    execfile_(filename, namespace)
  File "/home/docs/checkouts/readthedocs.org/user_builds/pytorch3d/envs/latest/lib/python3.11/site-packages/sphinx/util/pycompat.py", line 150, in execfile_
    exec_(code, _globals)
  File "/home/docs/checkouts/readthedocs.org/user_builds/pytorch3d/checkouts/latest/docs/conf.py", line 25, in <module>
    from recommonmark.parser import CommonMarkParser
  File "/home/docs/checkouts/readthedocs.org/user_builds/pytorch3d/envs/latest/lib/python3.11/site-packages/recommonmark/parser.py", line 6, in <module>
    from CommonMark import DocParser, HTMLRenderer
  File "/home/docs/checkouts/readthedocs.org/user_builds/pytorch3d/envs/latest/lib/python3.11/site-packages/CommonMark/__init__.py", line 3, in <module>
    from CommonMark.CommonMark import HTMLRenderer
  File "/home/docs/checkouts/readthedocs.org/user_builds/pytorch3d/envs/latest/lib/python3.11/site-packages/CommonMark/CommonMark.py", line 18, in <module>
    HTMLunescape = html.parser.HTMLParser().unescape
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'HTMLParser' object has no attribute 'unescape'
```

Reviewed By: shapovalov

Differential Revision: D47471545

fbshipit-source-id: 48e121e20da535b3cc46b6bd2393d28869067b8b
      57f6e792
    • Jeremy Reizenstein's avatar
      update wheel scripts · 2883a07b
      由 Jeremy Reizenstein 创作于 
      Summary: New versions of cuda etc. I haven't committed recent changes to this for a while

Reviewed By: shapovalov

Differential Revision: D47396136

fbshipit-source-id: d6c27f5056fa8f4a74a628fa1d831159000acf55
      2883a07b
  43. 13 7月, 2023 3 次提交
    • Jeremy Reizenstein's avatar
      switch to readthedocs.yaml · 6462aa60
      由 Jeremy Reizenstein 创作于 
      Summary: This is needed from september 2023. As a side effect, implicitron docs should build better because typing.get_args exists etc.

Reviewed By: shapovalov

Differential Revision: D47363855

fbshipit-source-id: a954c5b81b1e5a4435fca146a11aea0d2ca96f45
      6462aa60
    • Roman Shapovalov's avatar
      Read depth maps from OpenXR files · d851bc31
      由 Roman Shapovalov 创作于 
      Summary:
Blender uses OpenEXR to dump depth maps, so we have to support it.
OpenCV requires to explicitly accepth the vulnerabilities by setting the env var before exporting.
We can set it but I think it should be user’s responsibility.
OpenCV error reporting is adequate, so I don’t handle the error on our side.

Reviewed By: bottler

Differential Revision: D47403884

fbshipit-source-id: 2fcadd1df9d0efa0aea563bcfb2e3180b3c4d1d7
      d851bc31
    • Roman Shapovalov's avatar
      Fix: tensor vs array type correctness · 8164ac40
      由 Roman Shapovalov 创作于 
      Summary:
For fg-masking depth, we assumed np.array but passed a Tensor; for defining the default depth_mask, vice versa.

Note that we change the intended behaviour for the latter, assuming that 0s are areas with empty depth. When loading depth masks, we replace NaNs with zeros, so it is sensible. It is not a BC change as that branch would crash if executed. Since there was no reports, I assume no one cared.

Reviewed By: bottler

Differential Revision: D47403588

fbshipit-source-id: 1094104176d7d767a5657b5bbc9f5a0cc9da0ede
      8164ac40
  45. 06 7月, 2023 4 次提交
    • Emilien Garreau's avatar
      Avoid to keep in memory lengths and bins for ImplicitronRayBundle · 9446d91f
      由 Emilien Garreau 创作于 
      Summary:
Convert ImplicitronRayBundle to a "classic" class instead of a dataclass. This change is introduced as a way to preserve the ImplicitronRayBundle interface while allowing two outcomes:
- init lengths arguments is now a Optional[torch.Tensor] instead of torch.Tensor
- lengths is now a property which returns a `torch.Tensor`. The lengths property will either recompute lengths from bins or return the stored _lengths. `_lenghts` is None if bins is set. It saves us a bit of memory.

Reviewed By: shapovalov

Differential Revision: D46686094

fbshipit-source-id: 3c75c0947216476ebff542b6f552d311024a679b
      9446d91f
    • Emilien Garreau's avatar
      Adapt RayPointRefiner and RayMarcher to support bins. · 3d011a91
      由 Emilien Garreau 创作于 
      Summary:
## Context

Bins are used in mipnerf to allow to manipulate easily intervals. For example, by doing the following, `bins[..., :-1]` you will obtain all the left coordinates of your intervals, while doing `bins[..., 1:]` is equals to the right coordinates of your intervals.

We introduce here the support of bins like in MipNerf implementation.

## RayPointRefiner

Small changes have been made to modify RayPointRefiner.
- If bins is None

```
mids = torch.lerp(ray_bundle.lengths[..., 1:], ray_bundle.lengths[…, :-1], 0.5)
z_samples = sample_pdf(
		mids, # [..., npt]
		weights[..., 1:-1], # [..., npt - 1]
               ….
            )
```

- If bins is not None
In the MipNerf implementation the sampling is done on all the bins. It allows us to use the full weights tensor without slashing it.

```
z_samples = sample_pdf(
		ray_bundle.bins, # [..., npt + 1]
		weights, # [..., npt]
               ...
            )
```

## RayMarcher

Add a ray_deltas optional argument. If None, keep the same deltas computation from ray_lengths.

Reviewed By: shapovalov

Differential Revision: D46389092

fbshipit-source-id: d4f1963310065bd31c1c7fac1adfe11cbeaba606
      3d011a91
    • Emilien Garreau's avatar
      Add blurpool following MIPNerf paper. · 5910d81b
      由 Emilien Garreau 创作于 
      Summary:
Add blurpool has defined in [MIP-NeRF](https://arxiv.org/abs/2103.13415).
It has been added has an option for RayPointRefiner.

Reviewed By: shapovalov

Differential Revision: D46356189

fbshipit-source-id: ad841bad86d2b591a68e1cb885d4f781cf26c111
      5910d81b
    • Emilien Garreau's avatar
      Add integrated position encoding based on MIPNerf implementation. · ccf860f1
      由 Emilien Garreau 创作于 
      Summary: Add a new implicit module Integral Position Encoding based on [MIP-NeRF](https://arxiv.org/abs/2103.13415).

Reviewed By: shapovalov

Differential Revision: D46352730

fbshipit-source-id: c6a56134c975d80052b3a11f5e92fd7d95cbff1e
      ccf860f1