GitLab

Summary: The diff support colors in cubify for align = "center"

Reviewed By: bottler

Differential Revision: D53777011

fbshipit-source-id: ccb2bd1e3d89be3d1ac943eff08f40e50b0540d9

Summary: Add an option to run tests without the OpenGL Renderer.

Reviewed By: patricklabatut

Differential Revision: D53573400

fbshipit-source-id: 54a14e7b2f156d24e0c561fdb279f4a9af01b793

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

Summary: Build for new pytorch versions

Reviewed By: shapovalov

Differential Revision: D53266104

fbshipit-source-id: f7aaacaf39cab3839b24f45361c36f087d0ea7c9

Reviewed By: zsol

Differential Revision: D53258682

fbshipit-source-id: 3f006b5f31a2b1ffdc6323d3a3b08ac46c3162ce

Differential Revision: D53152021

fbshipit-source-id: 78be99b00abe4d992db844ff5877a89d42d468af

Differential Revision: D53111480

fbshipit-source-id: 0f506bf29cf908e40b058ae72f51e828cd597825

Differential Revision: D53059851

fbshipit-source-id: f5d0951186c858f90ddf550323a163e4b6d42b68

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

Summary: Fixed `get_rgbd_point_cloud` to take any number of image input channels.

Reviewed By: bottler

Differential Revision: D52796276

fbshipit-source-id: 3ddc0d1e337a6cc53fc86c40a6ddb136f036f9bc

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

Summary: Fix for https://github.com/facebookresearch/pytorch3d/issues/1708

Reviewed By: patricklabatut

Differential Revision: D52480756

fbshipit-source-id: 530c0f9413970fba042eec354e28318c96e35f42

Summary:
An OSS user has pointed out in https://github.com/facebookresearch/pytorch3d/issues/1703 that the output of matrix_to_quaternion (in that file) can be non standardized.

This diff solves the issue by adding a line of standardize at the end of the function

Reviewed By: bottler

Differential Revision: D52368721

fbshipit-source-id: c8d0426307fcdb7fd165e032572382d5ae360cde

Summary: Implement submeshing for TexturesAtlas and add associated test

Reviewed By: bottler

Differential Revision: D52334053

fbshipit-source-id: d54080e9af1f0c01551702736e858e3bd439ac58

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

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

Summary:
Porting this commit by davnov134 .
https://github.com/fairinternal/pytorch3d/commit/93a3a62800799c73758505c6397ac7a1440b18d9#diff-a8e107ebe039de52ca112ac6ddfba6ebccd53b4f53030b986e13f019fe57a378

Capability to interpret world/local coordinates with various align_corners semantics.

Reviewed By: bottler

Differential Revision: D51855420

fbshipit-source-id: 834cd220c25d7f0143d8a55ba880da5977099dd6

Differential Revision: D51902460

fbshipit-source-id: 3ffc5d7d2da5c5d4e971ee8275bd999c709e0b12

Summary: Fixes github.com/facebookresearch/pytorch3d/issues/1680

Reviewed By: MichaelRamamonjisoa

Differential Revision: D51587889

fbshipit-source-id: e68ae32d7041fb9ea3e981cf2bde47f947a41ca2

Summary:
diag_suppress is  deprecated from cuda

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1687

Reviewed By: MichaelRamamonjisoa

Differential Revision: D51495875

Pulled By: bottler

fbshipit-source-id: 6543a15e666238365719117bfcf5f7dac532aec1

Summary:
Change the data type usage in the code to ensure cross-platform compatibility
long -> int64_t

<img width="628" alt="image" src="https://github.com/facebookresearch/pytorch3d/assets/6214316/40041f7f-3c09-4571-b9ff-676c625802e9">

Tested under
Win 11 and Ubuntu 22.04
with
CUDA 12.1.1 torch 2.1.1

Related issues & PR

https://github.com/facebookresearch/pytorch3d/pull/9

https://github.com/facebookresearch/pytorch3d/issues/1679

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1689

Reviewed By: MichaelRamamonjisoa

Differential Revision: D51521562

Pulled By: bottler

fbshipit-source-id: d8ea81e223c642e0e9fb283f5d7efc9d6ac00d93

Summary: Fix recent flake complaints

Reviewed By: MichaelRamamonjisoa

Differential Revision: D51811912

fbshipit-source-id: 65183f5bc7058da910e4d5a63b2250ce8637f1cc

Differential Revision: D51645956

fbshipit-source-id: 1ae7279efa0a27bb9bc5255527bafebb84fdafd0

Summary: User confusion (https://github.com/facebookresearch/pytorch3d/issues/1579) about how zbuf is used for alpha compositing. Added small description and reference to paper to help give some context.

Reviewed By: bottler

Differential Revision: D51374933

fbshipit-source-id: 8c489a5b5d0a81f0d936c1348b9ade6787c39c9a

Summary: Fixes lint in test_render_points in the PyTorch3D library.

Differential Revision: D51289841

fbshipit-source-id: 1eae621eb8e87b0fe5979f35acd878944f574a6a

Summary:
When the ply format looks as follows:
  ```
comment TextureFile ***.png
element vertex 892
property double x
property double y
property double z
property double nx
property double ny
property double nz
property double texture_u
property double texture_v
```
`MeshPlyFormat` class will read uv from the ply file and read the uv map as commented as TextureFile.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1100

Reviewed By: MichaelRamamonjisoa

Differential Revision: D50885176

Pulled By: bottler

fbshipit-source-id: be75b1ec9a17a1ed87dbcf846a9072ea967aec37

Summary: Remove unused argument `mask_points` from `get_rgbd_point_cloud` and fix `get_implicitron_sequence_pointcloud`, which assumed it was used.

Reviewed By: MichaelRamamonjisoa

Differential Revision: D50885848

fbshipit-source-id: c0b834764ad5ef560107bd8eab04952d000489b8

Summary: fixes https://github.com/facebookresearch/pytorch3d/issues/1679

Reviewed By: MichaelRamamonjisoa

Differential Revision: D50949933

fbshipit-source-id: 5c467de8bf84dd2a3d61748b3846678582d24ea3

Summary: update

Reviewed By: MichaelRamamonjisoa

Differential Revision: D50806966

fbshipit-source-id: 95fd341c9e5e4e07b689eb71b3a729baff3b8192

Summary:
```
sed -i 's/startswith((\"1.13.\", \"2.0.\"))/startswith\(\"2.1.\"\)/' *b
```

Reviewed By: shapovalov

Differential Revision: D50806967

fbshipit-source-id: df19462564edb1f840753efeae96b516c7a9f764

Summary: Don't call tensor.cross() without dim, to avoid new warning.

Reviewed By: MichaelRamamonjisoa

Differential Revision: D49879590

fbshipit-source-id: e9ba83923b6dc3bcface6782b8b26729ab5b0a4c

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

Summary: Investigating a reported problem.

Reviewed By: MichaelRamamonjisoa

Differential Revision: D50791296

fbshipit-source-id: 8dc162b87d02debf05d16c2b4816fcd57234d7e0

Summary:
coodinates -> coordinates

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1656

Reviewed By: MichaelRamamonjisoa

Differential Revision: D50325515

Pulled By: bottler

fbshipit-source-id: 406d2e286ead4fa5e9080092b4918a748495ee23

Summary: Build updates for PyTorch 2.1

Reviewed By: MichaelRamamonjisoa

Differential Revision: D50345762

fbshipit-source-id: 89bf4edf1c21566aa86a3abca9b4df7c4d1d17a2

Differential Revision: D49531589

fbshipit-source-id: 61c28ae33d2e5f75fd1695f35dc99931a3aaf7d3

Summary:
This exposes a setting on VolumeSampler so you can change the padding_mode. This is very useful when using cameras inside a volume that doesn't cover the entire world. By setting the value to `border` you can get much better behavior than `zeros` which causes edge effects for things like the sky. Border emulates infinitely tall buildings instead.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1638

Test Plan:
Tested with torchdrive

Example before:
![image](https://github.com/facebookresearch/pytorch3d/assets/909104/e99ffb7c-c4ba-40f8-b15c-ad5d1b53f0df)

Example after:
![image](https://github.com/facebookresearch/pytorch3d/assets/909104/f8d9821b-93d5-44b5-b9d4-c1670711ddce)

Reviewed By: MichaelRamamonjisoa

Differential Revision: D49384383

Pulled By: bottler

fbshipit-source-id: 202b526e07320a18944c39a148beec94c0f5d68c

Summary: I think we include more thrust than needed, and maybe removing it will help things like  https://github.com/facebookresearch/pytorch3d/issues/1610 with DebugSyncStream errors on Windows.

Reviewed By: shapovalov

Differential Revision: D48949888

fbshipit-source-id: add889c0acf730a039dc9ffd6bbcc24ded20ef27

Summary: Python3 makes the use of `(object)` in class inheritance unnecessary. Let's modernize our code by eliminating this.

Reviewed By: itamaro

Differential Revision: D48673863

fbshipit-source-id: 032d6028371f0350252e6b731c74f0f5933c83cd

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