Pointcept: a codebase for point cloud perception research. Latest works: PTv3 (CVPR'24 Oral), PPT (CVPR'24), OA-CNNs (CVPR'24), MSC (CVPR'23)
Changelog:
Tasks:
(Hope I will have enough time to finish these tasks)
Changelog:
discrete_coord
to grid_coord
;Masked Scene Contrast
(MSC);PointContrast
and Contrastive Scene Contexts
;pointcept.utils.losses
to pointcept.models.losses
Voxelize
to GridSample
;max_batch_point
mechanism;PreciseEvaluator
as a default hook for semantic segmentation;DDP testing
(hook and test script).We upgraded the released codebase of Point Transformer V2 and named it Pointcept. Compared with the PTv2 released code, the main change is as follows:
hook
mechanism, which widely increases the flexibility of Pointcept.category
for classification label, segment
for semantic segmentation, instance
for instance segmentation, bbox
for object detection.