Hey, I'm Darren 👋

I am a computer vision and robotics engineer currently working on making boats autonomous on Australian waters through marine vessel and mammal detection 🚢 🐳 🌊

My PhD focused on 3D perception in autonomous vehicles with a focus on unsupervised domain adaptation to allow detectors to generalize across a variety of lidar types and environments without needing human-annotated labels for each new domain.

Publications 📖

MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaption in 3D Object Detection [paper][code]
(ITSC 2023) MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detection [paper][code]
(ICRA 2023) Viewer-Centred Surface Completion for Unsupervised Domain Adaptation in 3D Object Detection [paper][code]
(RA-L 2022) See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation [paper][code]
(ITSC 2021) Optimising the selection of samples for robust lidar camera calibration [paper][code]

Darren Tsai's Projects

kitti2bag

Convert KITTI dataset to ROS bag file the easy way!

lidar2cam

Projection of lidar pointcloud into a camera image for ROS

ms3d

Auto-labeling of point cloud sequences for 3D object detection using an ensemble of experts and temporal refinement

nuscenes2bag

nuScenes dataset to rosbag format

pytube

Pytube for downloading Youtube videos for free

see-mtda

(RA-L 2022) See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation.

see-vcn

(ICRA 2023) Viewer-Centred Surface Completion for Unsupervised Domain Adaptation in 3D Object Detection

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