©2019 Toronto Robotics and AI Laboratory

3D Object Detection

Object-centric stereo matching module that focuses on predicting the disparities of objects of interest to remove streaking artifacts.

Paper

Video

OC Stereo: Stereo 3D Object Detection

Alex D. Pon, Jason Ku, Chengyao Li, and Steven L. Waslander.

Object-Centric Stereo Matching for 3D Object Detection.

In submission.

Virtual Multi-View Synthesis module for improving orientation estimation of pedestrians.

Paper

Video

VMVS: 3D Pedestrian Orientation Estimation

Jason Ku, Alex D. Pon, Sean Walsh, and Steven L. Waslander.

Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation. IROS 2019.

Monocular 3D object detection method that uses proposals and leverages shape reconstruction. Can be found on the KITTI benchmark under MonoPSR.

Paper

Video

MonoPSR: Monocular 3D Object Detection

Jason Ku, Alex D. Pon, and Steven L. Waslander.

Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction. CVPR 2019.

LiDAR and image fusion for real-time 3D object detection.

Paper

Video

Code

AVOD: Aggregate View Object Detection

Jason Ku, Melissa Mozifian, Jungwook Lee, Ali Harakeh, and Steven L. Waslander. 

Joint 3D Proposal Generation and Object Detection from View Aggregation. IROS 2018.