Software and Datasets
Chengyao Li, Jason Ku, and Steven L. Waslander.
Confidence Guided Stereo 3D Object Detection with Split Depth Estimation.
Confidence-guided stereo 3D object detection pipeline that uses separate decoders for foreground and background pixels during depth estimation..
Alex D. Pon, Jason Ku, Chengyao Li, and Steven L. Waslander.
Object-Centric Stereo Matching for 3D Object Detection.
Object-centric stereo matching module that focuses on predicting the disparities of objects of interest to remove streaking artifacts.
Ali Harakeh, Michael Smart, Steven L. Waslander.
BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors.
An uncertainty estimation approach that reformulates the standard object detector inference and Non-Maximum suppression components from a Bayesian perspective.
Jason Ku, Alex D. Pon, Sean Walsh, and Steven L. Waslander.
Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation.
Virtual Multi-View Synthesis module for improving orientation estimation of pedestrians.
Jason Ku, Alex D. Pon, and Steven L. Waslander.
Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction.
Monocular 3D object detection method that uses proposals and leverages shape reconstruction. Can be found on the KITTI benchmark under MonoPSR.
Jason Ku, Melissa Mozifian, Jungwook Lee, Ali Harakeh, and Steven L. Waslander.
Joint 3D Proposal Generation and Object Detection from View Aggregation.
LiDAR and image fusion for real-time 3D object detection.