GitHub

Rethinking the Refinement Stage of 3D Object Detection: A Multi-Task Learning Perspective with Mixture-of-Experts

This is the official implementation of RefineMoE, our paper on enhancing two-stage 3D object detection. RefineMoE introduces a Multi-Task Learning approach to the refinement stage of 3D object ...
UCR Today

New adaptive optics to support gravitational-wave discoveries

LIGO is an observatory that detects gravitational waves — ripples in spacetime caused by massive accelerating objects like merging black holes. It was the first to confirm their existence, supporting ...
IEEE

MGAF: LiDAR-Camera 3D Object Detection with Multiple Guidance and Adaptive Fusion

Abstract: Recent years have witnessed the remarkable progress of 3D multi-modality object detection methods based on the Bird's-Eye-View (BEV) perspective. However, most of them overlook the ...
IEEE

ASCFormer: An Adaptive Strucure-aware Cascaded Transformer for 3D Object Detection

Abstract: 3D object detection has achieved significant progress in outdoor LiDAR point clouds, however, the inherent irregularity and varying sparsity distribution of point occupancy present a key ...
GitHub

A Baseline for 3D Multi-Object Tracking

Introduction 3D multi-object tracking (MOT) is an essential component technology for many real-time applications such as autonomous driving or assistive robotics. However, recent works for 3D MOT tend ...