Pytorch3d

A small release.

Minor new features
* Saving normals to OBJ https://github.com/facebookresearch/pytorch3d/commit/092400f1e79826cbb503b5f309c2d55cd5ca43ef
* Saving TexturesVertex to GLB https://github.com/facebookresearch/pytorch3d/commit/178a7774d4424ca2f0047a8d48aa40c39b67e1d2
* Implicitron evaluation works better when ground truth depth map not supplied https://github.com/facebookresearch/pytorch3d/commit/0e3138eca89336d222d9338687741da824a39443
* Implicitron can now read from a new dataset format which stores metadata in sqlite files. This requires the sqlalchemy library. https://github.com/facebookresearch/pytorch3d/commit/32e1992924929a9b79e880ed6f5bdc74089e8c73
Fixes
* Error in example in cameras.md https://github.com/facebookresearch/pytorch3d/commit/f5a117c74b3c34f1e2b4fb5dfa2e68dec2f42975
* Build fix with newer CUB https://github.com/facebookresearch/pytorch3d/commit/b921efae3e52dcd93e553db3d02378951e894769
* Warnings when we don’t obey user’s request of torch.use_deterministic_algorithms. Some cuda implementations in pytorch3d are non-deterministic. https://github.com/facebookresearch/pytorch3d/commit/ef5f620263562657a022dee419abd63534d123e7
* Loading bounding boxes in Co3D-type datasets in implicitron was failing when masks were not requested https://github.com/facebookresearch/pytorch3d/commit/7aeedd17a4140eef139987e946a7017df7a97433

A small release. We now support PyTorch 2.0.

Minor new features
* join_pointclouds_as_scene https://github.com/facebookresearch/pytorch3d/commit/a123815f40d19127ad8dc20ae93483303220046f
* OverfitModel for NeRF-style training with overfitting to one scene, a specific case of GenericModel https://github.com/facebookresearch/pytorch3d/commit/813e941de5084902fb07c5e95dc58314b9bf8a27


Improvements
* No relative imports in GenericModel, making the file easier to copy into a user’s project. https://github.com/facebookresearch/pytorch3d/commit/d388881f2ca41713d8e20c64c10abfa0c76b73cc
* Implicitron classes which are both nn.Modules and configurables now have simpler initialization, where user does not need to worry about calling nn.Module’s `__init__`. https://github.com/facebookresearch/pytorch3d/commit/9540c29023c2b6bb53e5a26a5e7a9d34ce88e9b1 https://github.com/facebookresearch/pytorch3d/commit/c8af1c45ca9f4fdd4e59b49172ca74983ff3147a
* Windows compilation fix https://github.com/facebookresearch/pytorch3d/commit/3388d3f0aa6bc44fe704fca78d11743a0fcac38c
* doc improvements: opencv cameras https://github.com/facebookresearch/pytorch3d/commit/18c38ad6006d046dc1d841d6020c6fbe6ad34a94
* Camera objects can now be iterated https://github.com/facebookresearch/pytorch3d/commit/84851c8312a709a95215d36adc103f7af97d5b5f
* Fixes for RayBundle plotting https://github.com/facebookresearch/pytorch3d/commit/9dc28f5dd5c529026cc47dfcc4dbf0d34dbaa67b
* Fixing bug in rasterizer.py caused by duplicate line (1421) https://github.com/facebookresearch/pytorch3d/commit/b95535c8b73299134bb2144a8b36edfffaf2e225
* Doc and fixes for get_rgbd_point_cloud, including new euclidean option https://github.com/facebookresearch/pytorch3d/commit/a12612a48fa6e3578294dc4f418d3abce10a7938
* Implicitron improvements to Co3D-style dataset and evaluation including to render_flyaround: https://github.com/facebookresearch/pytorch3d/commit/1de2d0c8207b0f3b7f6119eeae5562fe57efeea9 https://github.com/facebookresearch/pytorch3d/commit/d561f1913ed41e2e2a6b292f1c91fe8b96cbaf61 https://github.com/facebookresearch/pytorch3d/commit/54eb76d48c936da9848cfa56a6c487f45cb2ecf1 https://github.com/facebookresearch/pytorch3d/commit/3239594f78632fe207195e4622c00fb1656c4675 https://github.com/facebookresearch/pytorch3d/commit/11959e0b24933d80e41260dd47e95430a2e3c465 https://github.com/facebookresearch/pytorch3d/commit/a7256e4034376f3e802178da5e8498f8ba184888
* Version incrementing for inplace tensor modifications https://github.com/facebookresearch/pytorch3d/commit/7d8b029aaed5f247e3898f4b51e6a79ca52bfc54
* Implicitron’s components now ensure the registry is prefilled using a new extension point pre_expand. This is for compatibility with lazy import systems like cinder. https://github.com/facebookresearch/pytorch3d/commit/c759fc560f84eaff3577afac0083a2a2f07b349f
* Big refactor of Implicitron’s json_index_dataset, with much loading logic moved to a new FrameDataBuilder concept. https://github.com/facebookresearch/pytorch3d/commit/ebdbfde0cee9d6adca2c0508f1a664c13d3cd65a

A small release. Python 3.7 is no longer supported. We support from PyTorch 1.9.0 to PyTorch 1.13.0. [EDIT: post-release, builds for 1.13.1 have also been added.]

New feature
* Marching cubes now has an efficient CUDA implementation. https://github.com/facebookresearch/pytorch3d/commit/8b8291830e6ca1f5882700e214f114d5442a04db . Improvements to the cpu code too https://github.com/facebookresearch/pytorch3d/commit/1706eb8216248e54f68cad86f7ea4125c79a3ca4

Minor new features
* The experimental glTF support now allows writing meshes to GLB files, including with TexturesUV textures. https://github.com/facebookresearch/pytorch3d/commit/cc2840eb4408f8fd6ad0531e3a817d73e0a53e03
* Specification of param groups in implicitron made more flexible https://github.com/facebookresearch/pytorch3d/commit/7be49bf46fdce44ec41fc22d29e99d614c1988d6
* Implicitron’s loader for Co3D-style datasets can load multiple categories https://github.com/facebookresearch/pytorch3d/commit/e4a329814978934b2fda8fb92c2c14ebb42fa0b2
* Implicitron can be used without the lpips library being present. https://github.com/facebookresearch/pytorch3d/commit/322c8f2f50bb95e9d89c47126e081cb57395d116

Fixes
* Implicitron visualization https://github.com/facebookresearch/pytorch3d/commit/c3a6ab02da3192aa18cda85d66d957a11aacfa10 https://github.com/facebookresearch/pytorch3d/commit/94f321fa3dd776da5edd1efa80e8a094ee5e6b02
* Implicitron’s rasterize_mc https://github.com/facebookresearch/pytorch3d/commit/1706eb8216248e54f68cad86f7ea4125c79a3ca4
* Implicitron’s voxel grid, especially its scaffold https://github.com/facebookresearch/pytorch3d/commit/a1f2ded58a502f0d65c86ff6c86f417689a5c8d4 https://github.com/facebookresearch/pytorch3d/commit/bea84a6fcd9bf35950f32868deb9fb5b540c4534 https://github.com/facebookresearch/pytorch3d/commit/f711c4bfe9b1e3dcc968c3182bfb563dc0299893
* raysampling: The `origins` in a raybundle (which downstream code typically doesn’t use) were wrong when unit_directions=True https://github.com/facebookresearch/pytorch3d/commit/eff0aad15acf9125c1dae6820ae1414f783466f0

Documentation
* Fixes to readmes and readthedocs

This release brings a lot of fixes and improvements to implicitron.

PyTorch 1.8 is no longer supported. We support from PyTorch 1.9.0 to PyTorch 1.12.1.

New features
- Marching cubes fixes to existing python implementation, and fast C++ implementation for when data is on CPU https://github.com/facebookresearch/pytorch3d/commit/0d8608b9f99ac53d95256e124eaf9126e00adef5 https://github.com/facebookresearch/pytorch3d/commit/850efdf7065c238d4d1294d375278318005fd098
- New fisheye camera object. This involves a change to the API to allow such “nonlinear” cameras, i.e. those whose projection is not a projective transformation. In particular, get_projection_transform can now fail. https://github.com/facebookresearch/pytorch3d/commit/b0515e14615abe6e154f6dcf671ec8e54f29aaf4 https://github.com/facebookresearch/pytorch3d/commit/d19e6243d0294bf83a9f6debc6f55e14becf43b6 https://github.com/facebookresearch/pytorch3d/commit/84fa966643aa002b0075f3b4a0eddd22d1076a86 https://github.com/facebookresearch/pytorch3d/commit/8a96770dc28d393ebc2caacd18c7f5dfee8889a0


Minor new features
- get_se3_log function on Transform3D https://github.com/facebookresearch/pytorch3d/commit/9a0f9ae57280d5d38c9e59d0517599ccb834b81b
- get_rotation_to_best_fit_xy in circle_fitting https://github.com/facebookresearch/pytorch3d/commit/74bbd6fd76742466bc28134c9b8dfb99e4a677af
- Saving a mesh via IO to OBJ now includes TexturesUV texture https://github.com/facebookresearch/pytorch3d/commit/6ae6ff9cf73221ce60617ef4658b4892b986ba9d
- Checkerboard mesh utility https://github.com/facebookresearch/pytorch3d/commit/ce3fce49d7ad1a680d8c9be660164d5f7a0bb976
- Camera batches can now be indexed by bool tensors https://github.com/facebookresearch/pytorch3d/commit/b7c826b7863a4fb3c4ce0e10e5ed7400d32ed512
- Implicitron: You can just use a Configurable class straight away, you no longer need to call expand_args_fields or get_default_args first. https://github.com/facebookresearch/pytorch3d/commit/d6a197be3662cdfa57a34e3134fea1bb04eb1614
- Implicitron: In the newest pytorch versions, you can now use the faster `foreach` versions of optimizers https://github.com/facebookresearch/pytorch3d/commit/209c160a20ce4d87d4ca7a06f2975ba998765087
- Implicitron: full_image variants of psnr, l1 and lpips losses (ignoring mask). The masked image ones are renamed to make this clear. https://github.com/facebookresearch/pytorch3d/commit/7b985702bb660110dc70c2b8c6e6ed0a1a6bcd66 https://github.com/facebookresearch/pytorch3d/commit/d35781f2d79ffe5a895025ec386c47f7d77c085c
- Implicitron: Enable additional test-time source views for json dataset provider v2 https://github.com/facebookresearch/pytorch3d/commit/2ff2c7c836c2d47bb5b6fab57e7363862de6e423
- Implicitron: Option for filtering outlier input cameras in trajectory estimation https://github.com/facebookresearch/pytorch3d/commit/d281f8efd1e52172256ecdf21e82c7547f235ef2
- Implicitron: yaml configs to train selected methods on CO3Dv2 https://github.com/facebookresearch/pytorch3d/commit/1163eaab43af034ad36dce957511e32e6f7b8d62
- Implicitron raymarcher replicate_last_interval option. https://github.com/facebookresearch/pytorch3d/commit/611aba9a202886cf493d841610ae21c27401b923
- Mixed Frame Raysampling. You can now sample rays iid from a group of cameras, instead of a fixed number from each camera. This needed a new RayBundleHeterogeneous alternative to RayBundle. Implicitron now has its own raybundle object. https://github.com/facebookresearch/pytorch3d/commit/c311a4cbb93be458f8f48e7b269c6d3ee7fc2cf4 https://github.com/facebookresearch/pytorch3d/commit/ad8907d3738fbf4c80aa269954d1d8ba4f307530 https://github.com/facebookresearch/pytorch3d/commit/6ae863f301c66b82c8caf18e12cbae17d2620415


Major bug fix
- Implicitron: stratified_sampling no longer disabled https://github.com/facebookresearch/pytorch3d/commit/438c194ec61b34b377727c97d5922897546c581d https://github.com/facebookresearch/pytorch3d/commit/df36223ddf3b0bb75b9d9c080c5fe5dd940de34b

Bug fixes
- Cloned camera objects can now be saved with pickle and torch.save https://github.com/facebookresearch/pytorch3d/commit/efea540bbcab56fccde6f4bc729d640a403dac56
- Fix implicitron iteration time measurement https://github.com/facebookresearch/pytorch3d/commit/dd58ded73d049aa3143ee48c0c288195412594ce
- IOU3d fix for numerical stability https://github.com/facebookresearch/pytorch3d/commit/1bfe6bf20a1de877cc623d11c2eeed8c7091ae90
- Update SMPL url https://github.com/facebookresearch/pytorch3d/commit/5e7707b157861fd6ddb0564b6a727f79ea76fd56
- Implicitron doc fixes https://github.com/facebookresearch/pytorch3d/commit/fdaaa299a72eddbfff30a5f31fe2a643a2a4ca42 https://github.com/facebookresearch/pytorch3d/commit/4711d12a091ad31f51e761bee4a8cce7b4bab504
- Implicitron reduction feature aggregation broadcasting fix https://github.com/facebookresearch/pytorch3d/commit/73ba66e4abb14abd328d2e96f572337e04770cda
- Implicitron Fix for loading Co3Dv2’s point clouds https://github.com/facebookresearch/pytorch3d/commit/95a2acf7632241d09baff55e635e1e4904ed7505

Performance improvements
- Omit _check_valid_rotation_matrix by default https://github.com/facebookresearch/pytorch3d/commit/46cb5aaaae0cd40f729fd41a39c0c9a232b484c0
- _compute_vertex_normals does less work https://github.com/facebookresearch/pytorch3d/commit/a65928dcb965b114f3239603106e2b8e7c52b1c0
- Pulsar logging removed for performance gain https://github.com/facebookresearch/pytorch3d/commit/76234576868e96847097c6f6509f06a6fa9c0e5c
- VolumeSampler memory saving https://github.com/facebookresearch/pytorch3d/commit/4c8338b00f4a5b9dab31df6cecb5d21ce7ee0285
- Implicitron: Avoid extra CPU->GPU communication in raysampling https://github.com/facebookresearch/pytorch3d/commit/305cf32f6bfab02f735a938afed29d41d1759e4c
- Mesh rasterization on CPU now uses multiple threads https://github.com/facebookresearch/pytorch3d/commit/6471893f59f2c844c844be949bb64cccdcc5fdaa

Minor
- In implicitron, there are components in progress for voxel-grid-based implicit functions: decoders, voxel grids, param groups https://github.com/facebookresearch/pytorch3d/commit/edee25a1e5385ae62f37995dee1b5960b2a5ea66 https://github.com/facebookresearch/pytorch3d/commit/e7c609f1980780e1a3df1525011425ffd5aa4e7a https://github.com/facebookresearch/pytorch3d/commit/fe5bdb2fb501199e2be915b8f65859a970bbfd60 https://github.com/facebookresearch/pytorch3d/commit/24f5f4a3e7faec460e25ab0c1690f7d8329f92a6
- Implicitron config system fixes https://github.com/facebookresearch/pytorch3d/commit/4d9215b3b4851a209d24b19e4503360c08b42ea8 https://github.com/facebookresearch/pytorch3d/commit/da7fe2854eee7cdbba8b6c4b68065e857377591e https://github.com/facebookresearch/pytorch3d/commit/8339cf2610d3e1bbbe9ba4e86d65a216518ccceb
- Implicitron error improvements https://github.com/facebookresearch/pytorch3d/commit/a607dd063efde73288a3ffbd9c70f5447235e4fb
- Implicitron JsonIndexDataset fix for numpy.split warning https://github.com/facebookresearch/pytorch3d/commit/0b5def5257f53526ef81e1a83d462ef08af628d5
- Doc fix for IOU https://github.com/facebookresearch/pytorch3d/commit/a2659e1730a37345d882222464180a20a2547905 https://github.com/facebookresearch/pytorch3d/commit/60808972b8b1bffa9df770529d52099bfc286a01
- Doc fix for Implicitron base renderer https://github.com/facebookresearch/pytorch3d/commit/4711d12a091ad31f51e761bee4a8cce7b4bab504
- pytorch3d.ops doc fixes https://github.com/facebookresearch/pytorch3d/commit/6653f4400b0f8cd6cd66d042c49c60be28d06edd
- Lengths validation in chamfer and farthest_points https://github.com/facebookresearch/pytorch3d/commit/cb7bd33e7fd2c151a1676140ce7fb43ceb2b0663
- Implicitron visualize_reconstruction and render_flyaround improvements and fixes https://github.com/facebookresearch/pytorch3d/commit/6e25fe8cb312d6fa07ea5d7acfb608104f040a2d https://github.com/facebookresearch/pytorch3d/commit/3b3306f9b4c0de111644ad9d2ac5ffdecc5ee17c https://github.com/facebookresearch/pytorch3d/commit/f6d43eaa62fffa350a20b65121ac4d08b90807eb https://github.com/facebookresearch/pytorch3d/commit/c79c954dea6a7fcfed6839df09cf1ea4ac8907b3
- Implicitron compatibility with hydra 1.2 https://github.com/facebookresearch/pytorch3d/commit/90b758f7250239f353a046c9ef488ac8f17ecba1
- Implicitron SimpleDataLoaderMapProvider sample batches without replacement https://github.com/facebookresearch/pytorch3d/commit/73ea4187dec669f75f141ec11bdf0aef6ba4fe37
- Implicitron: visdom is now optional https://github.com/facebookresearch/pytorch3d/commit/ff933ab82b3fe63d67354714a58e8e3b497ebf00


Internal
- packed_to_padded now accepts all sizes https://github.com/facebookresearch/pytorch3d/commit/f34da3d3b6187b857a43cbf2dd5eeddf70833a3f
- test_opengl_utils unfriendly test fixed https://github.com/facebookresearch/pytorch3d/commit/9a1213e0e534a14b5f907ec4a0033bd9954034ef
- Implicitron: raybundle input to ImplicitFunctions has been made more consistent https://github.com/facebookresearch/pytorch3d/commit/72c3a0ebe59a7bc058c8f3a081ed9a2b7cb132bf
- location logic factored out of Volumes into a new VolumeLocator class so it can be reused in other objects. https://github.com/facebookresearch/pytorch3d/commit/f825f7e42caebdc61dd11997b485d4a7ed577068
- Sample_farthest_points uses CUB instead of a handwritten block reduction https://github.com/facebookresearch/pytorch3d/commit/8ea4da293846e64bee5cc99c8cb008888479947f
- Implicitron: MLP and Transformer have moved as they are no-longer only used by nerf. https://github.com/facebookresearch/pytorch3d/commit/898ba5c53be04b1c3ffbd981fcdb8f79b31767f4
- Cameras benchmarking https://github.com/facebookresearch/pytorch3d/commit/03562d87f5afd4004faff4f5d9a90261a62c8c7d
- Removed wrappers for eigh, solve, lstsq, and qr because we now rely on PyTorch 1.9 or greater https://github.com/facebookresearch/pytorch3d/commit/d4a1051e0f9f93a2052487cb42e34fe6e1987f84

This release brings **Implicitron** and **MeshRasterizerOpenGL**. There are builds for PyTorch 1.12.0, but no longer 1.7.x.

Large New Features
- Implicitron, a framework for new-view synthesis via modeling neural-network based representations. See [its README](projects/implicitron_trainer) for an introduction.
- MeshRasterizerOpenGL, a faster alternative to MeshRasterizer described in [Cole et al.](https://openaccess.thecvf.com/content/ICCV2021/papers/Cole_Differentiable_Surface_Rendering_via_Non-Differentiable_Sampling_ICCV_2021_paper.pdf). The speedup, which grows with mesh size, is about 20x on a 2M-faces-large mesh. This rasterizer is designed to work with SplatterPhongShader, a new per pixel lighting model. To use it, you must have [pycuda](https://github.com/inducer/pycuda/tree/main/pycuda) with the gl extension enabled, as well as [pyopengl](https://pypi.org/project/PyOpenGL/).

New features
- You can now choose to ignore the XY flip in cameras’ transform_points_screen [commit](https://github.com/facebookresearch/pytorch3d/commit/4372001981868657ea2111575dc8704404a25090)
- Fragments is now a dataclass with docstring and detach() [commit](https://github.com/facebookresearch/pytorch3d/commit/c21ba144e7b03562e28cb82341eb6b00d442f21c)
- SoftDepthShader and HardDepthShader for rendering depth maps [commit](https://github.com/facebookresearch/pytorch3d/commit/7e0146ece438f6de98a7ae930a339587311cb410) and [commit](https://github.com/facebookresearch/pytorch3d/commit/4ecc9ea89d55b51c6ad66996ff0edd013ded0815)
- AmbientLights can now be used to render an arbitrary number of channels (not just RGB) [commit](https://github.com/facebookresearch/pytorch3d/commit/8d10ba52b2c8aa59d6c54a193145492b1c196d4d)

Bug fixes

- Fix for loading PLY files with heterogenous faces (e.g. mixture of triangles and quadrilaterals [commit](https://github.com/facebookresearch/pytorch3d/commit/90d00f1b2be4b2f2c5eec40dd10894b2a449fbdf)
- Pointclouds.num_points_per_cloud now always returns a tensor [commit](https://github.com/facebookresearch/pytorch3d/commit/c6519f29f0512e209906f8265e0d049085670304)
- Chamfer fix for empty pointclouds [commit](https://github.com/facebookresearch/pytorch3d/commit/c6519f29f0512e209906f8265e0d049085670304)

For developers

- We are now using black 22.3 or later
- Tests should now be run from the pytorch3d root directory not the tests directory.

Minor
- In blending, pull common functionality into get_background_color [commit](https://github.com/facebookresearch/pytorch3d/commit/ea5df60d72307378d4c0641519e4e7a3671458dc)
- raising translated errors with `from None` so a simpler traceback is printed https://github.com/facebookresearch/pytorch3d/commit/8e0c82b89a96a1f1bed1ae5b84bd37524d0fe154
- PnP test fix [commit](https://github.com/facebookresearch/pytorch3d/commit/379c8b27803ce527387854ea9f7f612170a5ecbb)
- fix test which had cuda indexes of a cpu tensor [commit](https://github.com/facebookresearch/pytorch3d/commit/f4dd151037e4a534499f4e90ce918103f17436dd)

This release brings new targets and many improvements.

Builds for PyTorch 1.10.1, 1.10.2, 1.11.0, but no longer 1.6.0. Builds for Python 3.10 but no longer 3.6.

New Features
- MultinomialRaysampler and NDCMultinomialRaysampler replace GridRaysampler and NDCGridRaysampler [commit](https://github.com/facebookresearch/pytorch3d/commit/3eb4233844a8a3c6441e91ebe22a4354da8f5fae) which can sample using the new n_rays input and also bring stratified sampling along rays and direction normalization (also [commit](https://github.com/facebookresearch/pytorch3d/commit/67778caee87b5852250ad4c15d17d7c608e6f1bc)
- Function join_cameras_as_batch [commit](https://github.com/facebookresearch/pytorch3d/commit/39bb2ce06301d8085e8003a7e536aa72d5c969c6)
- Function join_pointclouds_as_batch [commit](https://github.com/facebookresearch/pytorch3d/commit/262c1bfcd4a25e7ab796573644968e4d843b7ffe)
- Camera batches can be indexed [commit](https://github.com/facebookresearch/pytorch3d/commit/28ccdb73280a2b2bc47d1202f922df67b3b2e63e) and [commit](https://github.com/facebookresearch/pytorch3d/commit/d67662d13ce497e746196f68cfd90b61954fea23)
- Meshes.submesh function to take a set of faces from a mesh. [commit](https://github.com/facebookresearch/pytorch3d/commit/22f86072ca1cda37a679fc7937311af47bf8fa3b) and [commit](https://github.com/facebookresearch/pytorch3d/commit/050f650ae84b07fb430617a8db65d257e5df129a)
- L1 support for KNN and chamfer [commit](https://github.com/facebookresearch/pytorch3d/commit/67fff956a26c0abdc4f3ddb495b61c8935972bf1)

Bug fixes
- Rasterizer.to broken without cameras [commit](https://github.com/facebookresearch/pytorch3d/commit/c371a9a6ccec687a298a3c23cd3d4c673f039eed)
- Joining batches of meshes with TexturesAtlas and TexturesUV broke first input meshes’ texture [commit](https://github.com/facebookresearch/pytorch3d/commit/4a1f1760540b791e638c5bcbb974b59583a0ada8)
- Transform3D.stack was entirely broken. [commit](https://github.com/facebookresearch/pytorch3d/commit/c8f3d6bc0bc366d44c8fca790c5e433503c7785f) which also added typing.
- The function cameras_from_opencv_projection always created on CPU 1021 [commit](https://github.com/facebookresearch/pytorch3d/commit/45d096e219379bd0b3d14bbe4633b09f818f988d)
- Batching didn’t work for AmbientLights 1043 [commit](https://github.com/facebookresearch/pytorch3d/commit/9e2bc3a17faf7dfffad9b0803f335da328b08a61)
- Pointclouds.subsample failed on windows 1015 [commit](https://github.com/facebookresearch/pytorch3d/commit/d6a12afbe77f8129b9285b30343b33e9cbf1bdec)
- Fit_textured_meshes tutorial now turns off perspective_correct in the final optimization, to avoid nans. [commit](https://github.com/facebookresearch/pytorch3d/commit/7ea0756b05d58938ea25c0cd05f37f35524000d0)

Improvements
- Points_normals much faster through use of symeig workaround [commit](https://github.com/facebookresearch/pytorch3d/commit/c2862ff42706ae98ce4053e7d76959f05fb2c3b3)
- A warning is now printed to console on rasterizer bin overflow [commit](https://github.com/facebookresearch/pytorch3d/commit/6726500ad39f1f135464b50086dc47953f98a4bb)

Small improvements
- [MeshRendererWithFragments](https://github.com/facebookresearch/pytorch3d/commit/57a33b25c1105b8424ca4ec927d19d530f03d3eb) and [matrix_to_axis_angle](https://github.com/facebookresearch/pytorch3d/commit/1cbf80dab6611efa305345fd8047bf6e2e4cbe6a) made more importable
- FacePointDistance, FacePointDistance and point_mesh_face_distance get min_triangle_area argument [commit](https://github.com/facebookresearch/pytorch3d/commit/471b12681888d37e15bd3fe6ae2b70032f06c026) - default also changed in [commit](https://github.com/facebookresearch/pytorch3d/commit/ee71c7c44786e41049829a5e461ce860d80a80c7)
- Fix for small faces in IoU3D [commit](https://github.com/facebookresearch/pytorch3d/commit/ccfb72cc502cc3fe30e168fcd220791ee8e449a2)
- Lower the epsilon value in the IoU3D [commit](https://github.com/facebookresearch/pytorch3d/commit/3de41223dde5facc3ba5c445e2cb11e6b4410d6d)
- Flexible background color for point compositing [commit](https://github.com/facebookresearch/pytorch3d/commit/59972b121d8c7bfc0e156b5ad5fcd77c11874178) and [commit](https://github.com/facebookresearch/pytorch3d/commit/0e377c6850f96b881680d40b7bce1e0104a10793)
- In points_to_volumes, the rescaling of features is now optional. [commit](https://github.com/facebookresearch/pytorch3d/commit/78fd5af1a6c8174fd3f6f4080e218a55f0ba6fce)
- LinearWithRepeat layer clarified and moved inside PyTorch3D from the NeRF project [commit](https://github.com/facebookresearch/pytorch3d/commit/2a1de3b610b8f2e95b3aeda6de36805a0baa0e9d)
- HarmonicEmbedding moved inside pytorch3d from projects/nerf. [commit](https://github.com/facebookresearch/pytorch3d/commit/f9a26a22fcd6f7f16eae7dc8fd6e48ecadd7486b) and [commit](https://github.com/facebookresearch/pytorch3d/commit/52c71b88169350bbeda0c18aaa73d6c9eeab5524)
- Invalid default values in Meshes.__init__ removed [commit](https://github.com/facebookresearch/pytorch3d/commit/aab95575a64dc43b8e24f49976cc263741efa47a)
- Support obj files missing usemtl declarations [commit]( https://github.com/facebookresearch/pytorch3d/commit/ef21a6f6aaeae499f60af9eb3e57ba41040aac11)
- CamerasBase.unproject_points typing [commit](https://github.com/facebookresearch/pytorch3d/commit/5053142363afca730c44ed2bd1a6aa24d4fc7635)
- Fix for Pointclouds.__init__ in certain cases with None in a list [commit](https://github.com/facebookresearch/pytorch3d/commit/fc4dd80208bbcf6f834e7e1594db0e106961fd60)
- Consistency validation for sampling_mode in joining TexturesUV [commit](https://github.com/facebookresearch/pytorch3d/commit/b51be58f634698486c1b283c1094d82748473b75)
- Doc fix for camera space fix from v0.6.1 [commit](https://github.com/facebookresearch/pytorch3d/commit/eb2bbf843311e76c6cf356fc9b9442896d85f89e)
- Doc fix for renderer pictures [commit](https://github.com/facebookresearch/pytorch3d/commit/c3c4495c7ac8181be47e49ed2bc935d340e47981)
- New ndc_grid_sample to handle grid-sampling using our NDC conventions [commit](https://github.com/facebookresearch/pytorch3d/commit/12f20d799e06e4ef16dd32686bf5a33e87c56c91)
- Fix scatter_ error in cubify on CPU [commit](https://github.com/facebookresearch/pytorch3d/commit/4c48beb226a97a26d4d8b480ae5ecf5fc8812742)
- In Transform3D, fix some dtype inconsistencies [commit](https://github.com/facebookresearch/pytorch3d/commit/b602edccc4c991a37adcf911726f2e2eb75a74f3)
- Fixes to make windows builds happier [commit](https://github.com/facebookresearch/pytorch3d/commit/f2cf9d4d0be34d3f7ecb4178c356cdfc34b7634c)

Internal
- Rename pytorch3d.common.types to pytorch3d.common.datatypes [commit](https://github.com/facebookresearch/pytorch3d/commit/f816568735b428e3b5546fee2348ac3abc8696de)
- Cleanup in ply_io [commit](https://github.com/facebookresearch/pytorch3d/commit/967a099231f10f0ebbbe93bc448db18a94fd976c)
- A major new feature, a framework for new-view synthesis via modeling neural-network based representations, called implicitron, is work in progress.
- We now use usort not isort for sorting imports.
- Future proofing calls to torch.meshgrid [commit](https://github.com/facebookresearch/pytorch3d/commit/1701b76a31e3e8c97d51b49dfcaa060762ab3764) and symeig [commit](https://github.com/facebookresearch/pytorch3d/commit/db1f7c45064a8e7b0cabe44cb5b9060daee15fb3) also [commit](https://github.com/facebookresearch/pytorch3d/commit/4d043fc9ac79d917ec1a72a23aa66a1589c58c7c). Also future proofing tests for a change to autograd behaviour that inplace operations don’t need to return the same object [commit](https://github.com/facebookresearch/pytorch3d/commit/feb5d36394b28e382e9a58e670fb5a92684bb4bb)
- Future proofing for the loss of TH headers in pytorch (needed for PyTorch 1.11) [commit](https://github.com/facebookresearch/pytorch3d/commit/069c9fd759461b60f089dd01f6779f9437a5695f) and [commit](https://github.com/facebookresearch/pytorch3d/commit/f8fe9a2be144cf3c7c047e05d59605474f3a8bdb)
- Base class for shaders introduced [commit](https://github.com/facebookresearch/pytorch3d/commit/96889deab99773b5df3f9313878f562771e99daa)