Darren Tsai's repositories
AtlasNet
This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.
canonical-capsules
Canonical Capsules: Self-Supervised Capsules in Canonical Pose (NeurIPS 2021)
Cylinder3D
Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
DINE
code for our CVPR 2022 paper "DINE: Domain Adaptation from Single and Multiple Black-box Predictors"
IA-SSD
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (CVPR 2022, Oral)
KITTI-Dataset
Visualising LIDAR data from KITTI dataset.
kitti2bag
Convert KITTI dataset to ROS bag file the easy way!
lidar2cam
Projection of lidar pointcloud into a camera image for ROS
mmdetection
OpenMMLab Detection Toolbox and Benchmark
nuscenes2bag
nuScenes dataset to rosbag format
ONCE_Benchmark
One Million Scenes for Autonomous Driving
OpenPCDet
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
pcn
Code for PCN: Point Completion Network in 3DV'18 (Oral)
PoinTr
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
pytube
Pytube for downloading Youtube videos for free
SparseKD
(NeurlPS 2022) Towards Efficient 3D Object Detection with Knowledge Distillation
ST3D
(CVPR 2021 & T-PAMI 2022) ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection & ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection
waymo-rosbag-record
tool to convert waymo open dataset to rosbag