Benchmarking different FlashAttention and FlashAttention-v2 implementations

[NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Code apapted from https://github.com/ethz-asl/hand_eye_calibration/blob/master/LICENSE to run as a python package without ROS or Catkin

C++ implementaton of the scalar-valued autograd engine and a simple neural net library built using the same

Image denoising using convolutional denoising autoencoders

Pointcept: a codebase for point cloud perception research. Latest works: PTv3 (CVPR'24 Oral), PPT (CVPR'24), OA-CNNs (CVPR'24), MSC (CVPR'23)