| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2024-09-13 | 885 Bytes | |
| Version 0.7.8 source code.tar.gz | 2024-09-13 | 36.4 MB | |
| Version 0.7.8 source code.zip | 2024-09-13 | 37.0 MB | |
| Totals: 3 Items | 73.4 MB | 0 | |
This version supports PyTorch 2.1 to 2.4
New feature * hausdorff distance / Add "max" point reduction for chamfer distance https://github.com/facebookresearch/pytorch3d/commit/44702fdb4ba0f80e96bee724766c545d4d93509c * limited support for AMD GPUs. Pulsar not included
Improvements * allow matrix_to_quaternion onnx export https://github.com/facebookresearch/pytorch3d/commit/7edaee71a9583f8f1eedf91187aa77a0797c38e0 * remove dependency on fvcore https://github.com/facebookresearch/pytorch3d/commit/4df110b0a94786bc6a312e6f5214ae6990492d88
Fixes * obj material loading when some unspecified names but not all https://github.com/facebookresearch/pytorch3d/commit/9acdd67b831f2d3d9db249b1c46d42139024cebf * Fix: setting FrameData.crop_bbox_xywh for backwards compatibility https://github.com/facebookresearch/pytorch3d/commit/d0d0e020071c34ffa0953c00f9e85be0672b597e