Skip to content

GitLab

Switch branch/tag
  1. 06 Jul, 2023 5 commits
    • Emilien Garreau's avatar
      Avoid to keep in memory lengths and bins for ImplicitronRayBundle · 9446d91f
      Emilien Garreau authored 
      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
      Emilien Garreau authored 
      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
      Emilien Garreau authored 
      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
      Emilien Garreau authored 
      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
    • Emilien Garreau's avatar
      Add utils to approximate the conical frustums as multivariate gaussians. · 29b8ebd8
      Emilien Garreau authored 
      Summary:
Introduce methods to approximate the radii of conical frustums along rays as described in [MipNerf](https://arxiv.org/abs/2103.13415):

- Two new attributes are added to ImplicitronRayBundle: bins and radii. Bins is of size n_pts_per_ray + 1. It allows us to manipulate easily and n_pts_per_ray intervals. For example we need the intervals coordinates in the radii computation for \(t_{\mu}, t_{\delta}\). Radii are used to store the radii of the conical frustums.

- Add 3 new methods to compute the radii:
   - approximate_conical_frustum_as_gaussians: It computes the mean along the ray direction, the variance of the
      conical frustum  with respect to t and variance of the conical frustum with respect to its radius. This
      implementation follows the stable computation defined in the paper.
   - compute_3d_diagonal_covariance_gaussian: Will leverage the two previously computed variances to find the
     diagonal covariance of the Gaussian.
   - conical_frustum_to_gaussian: Mix everything together to compute the means and the diagonal covariances along
     the ray of the Gaussians.

- In AbstractMaskRaySampler, introduces the attribute `cast_ray_bundle_as_cone`. If False it won't change the previous behaviour of the RaySampler. However if True, the samplers will sample `n_pts_per_ray +1` instead of `n_pts_per_ray`. This points are then used to set the bins attribute of ImplicitronRayBundle. The support of HeterogeneousRayBundle has not been added since the current code does not allow it. A safeguard has been added to avoid a silent bug in the future.

Reviewed By: shapovalov

Differential Revision: D45269190

fbshipit-source-id: bf22fad12d71d55392f054e3f680013aa0d59b78
      29b8ebd8
  3. 05 Jul, 2023 1 commit
  5. 16 Jun, 2023 5 commits
  7. 14 Jun, 2023 4 commits
  9. 13 Jun, 2023 2 commits
  11. 07 Jun, 2023 1 commit
  13. 26 May, 2023 1 commit
  15. 24 May, 2023 1 commit
  17. 22 May, 2023 1 commit
    • Roman Shapovalov's avatar
      Serialising dynamic arrays in SQL; read-only SQLite connection in SQL Dataset · d2119c28
      Roman Shapovalov authored 
      Summary:
1. We may need to store arrays of unknown shape in the database. It implements and tests serialisation.

2. Previously, when an inexisting metadata file was passed to SqlIndexDataset, it would try to open it and create an empty file, then crash. We now open the file in a read-only mode, so the error message is more intuitive. Note that the implementation is SQLite specific.

Reviewed By: bottler

Differential Revision: D46047857

fbshipit-source-id: 3064ae4f8122b4fc24ad3d6ab696572ebe8d0c26
      d2119c28
  19. 19 May, 2023 1 commit
    • Jeremy Reizenstein's avatar
      resources fix · ff80183f
      Jeremy Reizenstein authored 
      Summary: I don't know why RE tests sometimes fail here, but maybe it's a race condition. If that's right, this should fix it.

Reviewed By: shapovalov

Differential Revision: D46020054

fbshipit-source-id: 20b746b09ad9bd77c2601ac681047ccc6cc27ed9
      ff80183f
  21. 17 May, 2023 1 commit
    • Roman Shapovalov's avatar
      Refactor: FrameDataBuilder is more extensible. · b0462598
      Roman Shapovalov authored 
      Summary:
This is mostly a refactoring diff to reduce friction in extending the frame data.

Slight functional changes: dataset getitem now accepts (seq_name, frame_number_as_singleton_tensor) as a non-advertised feature. Otherwise this code crashes:
```
item = dataset[0]
dataset[item.sequence_name, item.frame_number]
```

Reviewed By: bottler

Differential Revision: D45780175

fbshipit-source-id: 75b8e8d3dabed954a804310abdbd8ab44a8dea29
      b0462598
  23. 14 May, 2023 1 commit
    • Virendra Kumar Pathak's avatar
      Softly deprecate the get_str=False flag. · d08fe6d4
      Virendra Kumar Pathak authored 
      Summary: We don't want to use print directly in stats.print() method. Instead this method will return the output string to the caller.

Reviewed By: shapovalov

Differential Revision: D45356240

fbshipit-source-id: 2cabe3cdfb9206bf09aa7b3cdd2263148a5ba145
      d08fe6d4
  25. 10 May, 2023 2 commits
    • Jeremy Reizenstein's avatar
      version 0.7.4 · 297020a4
      Jeremy Reizenstein authored 
      Summary: version number

Reviewed By: shapovalov

Differential Revision: D45704549

fbshipit-source-id: d63867f305b07c30ed9ea104f1494d23710fdbb7
      297020a4
    • Jeremy Reizenstein's avatar
      builds for PyTorch 2.0.1; drop 1.9 · 062e6c54
      Jeremy Reizenstein authored 
      Summary: Drop support for PyTorch 1.9.0 and 1.9.1.

Reviewed By: shapovalov

Differential Revision: D45704329

fbshipit-source-id: c0fe3ecf6a1eb9bcd4163785c0cb4bf4f5060f50
      062e6c54
  27. 09 May, 2023 1 commit
    • Roman Shapovalov's avatar
      Fix: FrameDataBuilder working with PathManager · c80180c9
      Roman Shapovalov authored 
      Summary: In refactoring, we lost path manager here, which broke manifold storage. Fixing this.

Reviewed By: bottler

Differential Revision: D45574940

fbshipit-source-id: 579349eaa654215a09e057be57b56b46769c986a
      c80180c9
  29. 08 May, 2023 1 commit
  31. 07 May, 2023 1 commit
    • dhb's avatar
      allow saving vertex normal in save_obj (#1511) · 092400f1
      dhb authored 
      Summary:
Although we can load per-vertex normals in `load_obj`, saving per-vertex normals is not supported in `save_obj`.

This patch fixes this by allowing passing per-vertex normal data in `save_obj`:
``` python
def save_obj(
    f: PathOrStr,
    verts,
    faces,
    decimal_places: Optional[int] = None,
    path_manager: Optional[PathManager] = None,
    *,
    verts_normals: Optional[torch.Tensor] = None,
    faces_normals: Optional[torch.Tensor] = None,
    verts_uvs: Optional[torch.Tensor] = None,
    faces_uvs: Optional[torch.Tensor] = None,
    texture_map: Optional[torch.Tensor] = None,
) -> None:
    """
    Save a mesh to an .obj file.

    Args:
        f: File (str or path) to which the mesh should be written.
        verts: FloatTensor of shape (V, 3) giving vertex coordinates.
        faces: LongTensor of shape (F, 3) giving faces.
        decimal_places: Number of decimal places for saving.
        path_manager: Optional PathManager for interpreting f if
            it is a str.
        verts_normals: FloatTensor of shape (V, 3) giving the normal per vertex.
        faces_normals: LongTensor of shape (F, 3) giving the index into verts_normals
            for each vertex in the face.
        verts_uvs: FloatTensor of shape (V, 2) giving the uv coordinate per vertex.
        faces_uvs: LongTensor of shape (F, 3) giving the index into verts_uvs for
            each vertex in the face.
        texture_map: FloatTensor of shape (H, W, 3) representing the texture map
            for the mesh which will be saved as an image. The values are expected
            to be in the range [0, 1],
    """
```

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1511

Reviewed By: shapovalov

Differential Revision: D45086045

Pulled By: bottler

fbshipit-source-id: 666efb0d2c302df6cf9f2f6601d83a07856bf32f
      092400f1
  33. 05 May, 2023 4 commits
  35. 04 May, 2023 2 commits
    • Jeremy Reizenstein's avatar
      nondeterminism warnings · ef5f6202
      Jeremy Reizenstein authored 
      Summary: do like xformers.

Reviewed By: shapovalov

Differential Revision: D44541873

fbshipit-source-id: 2c23160591cd9026fcd4972998d1bc90adba1356
      ef5f6202
    • Roman Shapovalov's avatar
      More tests for SQL Dataset · 3e3644e5
      Roman Shapovalov authored 
      Summary:
I forgot to include these tests to D45086611 when transferring code from pixar_replay repo.

They test the new ORM types used in SQL dataset and are SQL Alchemy 2.0 specific.

An important test for extending types is a proof of concept for generality of SQL Dataset. The idea is to extend FrameAnnotation and FrameData in parallel.

Reviewed By: bottler

Differential Revision: D45529284

fbshipit-source-id: 2a634e518f580c312602107c85fc320db43abcf5
      3e3644e5
  37. 01 May, 2023 1 commit
    • Ilia Vitsnudel's avatar
      Adding save mesh into glb file in TexturesVertex format · 178a7774
      Ilia Vitsnudel authored 
      Summary:
Added a suit of functions and code additions to experimental_gltf_io.py file to enable saving Meshes in TexturesVertex format into .glb file.
Also added a test to tets_io_gltf.py to check the functionality with the test described in Test Plane.

Reviewed By: bottler

Differential Revision: D44969144

fbshipit-source-id: 9ce815a1584b510442fa36cc4dbc8d41cc3786d5
      178a7774
  39. 27 Apr, 2023 1 commit
    • Emilien Garreau's avatar
      Simplify _xy_grid computation in raysampling · 823ab75d
      Emilien Garreau authored 
      Summary: Remove the need of tuple and reversed in the raysampling xy_grid computation

Reviewed By: bottler

Differential Revision: D45269342

fbshipit-source-id: d0e4c0923b9a2cca674b35e8d64862043a0eab3b
      823ab75d
  41. 25 Apr, 2023 1 commit
    • Roman Shapovalov's avatar
      SQL Index Dataset · 32e19929
      Roman Shapovalov authored 
      Summary:
Moving SQL dataset to PyTorch3D. It has been extensively tested in pixar_replay.

It requires SQLAlchemy 2.0, which is not supported in fbcode. So I exclude the sources and tests that depend on it from buck TARGETS.

Reviewed By: bottler

Differential Revision: D45086611

fbshipit-source-id: 0285f03e5824c0478c70ad13731525bb5ec7deef
      32e19929
  43. 20 Apr, 2023 1 commit
    • Roman Shapovalov's avatar
      When bounding boxes are cached in metadata, don’t crash on load_masks=False · 7aeedd17
      Roman Shapovalov authored 
      Summary:
We currently support caching bounding boxes in MaskAnnotation. If present, they are not re-computed from the mask. However, the masks need to be loaded for the bbox to be set.

This diff fixes that. Even if load_masks / load_blobs are unset, the bounding box can be picked up from the metadata.

Reviewed By: bottler

Differential Revision: D45144918

fbshipit-source-id: 8a2e2c115e96070b6fcdc29cbe57e1cee606ddcd
      7aeedd17
  45. 18 Apr, 2023 1 commit