3D Object Detection

Monocular 3D Object Detection

mono3D.png

Cody Reading, Ali Harakeh, Julia Chae, Steven L. Waslander.

Categorical Depth Distribution Network for Monocular 3D Object Detection.

CVPR 2021 (Oral).

Monocular 3D object detection pipeline that estimates pixel-wise categorical depth distributions to accurately locate image information in 3D space. 

Code

Paper

CG Stereo: Confidence Guided Stereo 3D Object Detection

CG Stereo.png

Chengyao Li, Jason Ku, and Steven L. Waslander.

Confidence Guided Stereo 3D Object Detection with Split Depth Estimation.

IROS 2020.

Confidence-guided stereo 3D object detection pipeline that uses separate decoders for foreground and background pixels during depth estimation.

Paper

Video

OC Stereo: Stereo 3D Object Detection

oc_stereo.png

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

Object-Centric Stereo Matching for 3D Object Detection.

ICRA 2020.

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

Paper

Video

BayesOD: Uncertainty Estimation in Deep Object Detectors

bayesOD.png

Ali Harakeh, Michael Smart, Steven L. Waslander. 

BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors

ICRA 2020.

An uncertainty estimation approach that reformulates the standard object detector inference and Non-Maximum suppression components from a Bayesian perspective.

Paper

Code

VMVS: 3D Pedestrian Orientation Estimation

vmvs_16:9.png

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.

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

Paper

Video

MonoPSR: Monocular 3D Object Detection

monopsr_16_9.png

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

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

CVPR 2019.

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

Paper

Video

Code

AVOD: Aggregate View Object Detection

avod.png

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

Joint 3D Proposal Generation and Object Detection from View Aggregation

IROS 2018.

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

Paper

Video

Code