AOP-Net: All-in-One Perception Network for Joint LiDAR-based 3D Object Detection and Panoptic Segmentation

no code implementations • 2 Feb 2023 • YiXuan Xu, Hamidreza Fazlali, Yuan Ren, Bingbing Liu

In this method, a dual-task 3D backbone is developed to extract both panoptic- and detection-level features from the input LiDAR point cloud.

3D Object Detection Autonomous Vehicles +5

A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation

no code implementations • CVPR 2022 • Hamidreza Fazlali, YiXuan Xu, Yuan Ren, Bingbing Liu

In our method, the 3D object detection backbone in Bird's-Eye-View (BEV) plane is augmented by the injection of Range-View (RV) feature maps from the 3D panoptic segmentation backbone.

3D Object Detection Autonomous Driving +4