This version supports PyTorch 2.2.0

New features

• We can now read UV textures from a PLY file https://github.com/facebookresearch/pytorch3d/pull/1100
• Align_corners switch in Volumes https://github.com/facebookresearch/pytorch3d/commit/94da8841af444312da13a1e2d96924e44a9d0d10
• submeshing now supports TexturesUV and TexturesAtlas https://github.com/facebookresearch/pytorch3d/commit/8a27590c5fd6aba4d138660614c7a18832701671 https://github.com/facebookresearch/pytorch3d/commit/e46ab49a34aebe8ca4f3de62b06be2d84e09a2ce
• Colors in cubify https://github.com/facebookresearch/pytorch3d/commit/ae9d8787ce4be8be6ac87eeac6ed82ca02919056

Improvements

• PointsRenderer documentation https://github.com/facebookresearch/pytorch3d/commit/3b4f8a4980e889936650e6841c6861ac45ed1117
• Made TexturesUVs more efficient https://github.com/facebookresearch/pytorch3d/commit/06cdc313a7996a3363e78b19edaf893f4454ba1c
• Numerical stability improved in so3_log_map / so3_exp_map https://github.com/facebookresearch/pytorch3d/commit/292acc71a33bf389225ef02af237dd82a8319f59
• get_rgbd_point_cloud takes any number of channels, not just RGB https://github.com/facebookresearch/pytorch3d/commit/799c1cd21beff84e50ac4ab7a480e715780da2de

Fixes

• Fix to C++ marching cubes https://github.com/facebookresearch/pytorch3d/commit/c292c71c1adb0712c12cf4fa67a7a84ad9b44e5c
• Fix to cuda marching cubes (which was broken in 0.7.5) https://github.com/facebookresearch/pytorch3d/commit/f61368255184694483db6d42a329f6d92b9f597d https://github.com/facebookresearch/pytorch3d/commit/7606854ff7d87b2b3ae99102d9868de57b88f9df
• Remove unused argument mask_points from get_rgbd_point_cloud and fix get_implicitron_sequence_pointcloud, which assumed it was used https://github.com/facebookresearch/pytorch3d/commit/f4f22092712251d9bf0f01519dbadb1419480ae0
• Standardize matrix_to_quaternion output https://github.com/facebookresearch/pytorch3d/commit/3087ab7f62b5d581a133e54849d462f37fdf4c2d