Deep neural networks (DNNs) have been proven extremely susceptible to
ad...
This work explores the use of 3D generative models to synthesize trainin...
Recent multi-camera 3D object detectors usually leverage temporal inform...
In this technical report, we present our solution, dubbed MV-FCOS3D++, f...
Due to the inherent ill-posed nature of 2D-3D projection, monocular 3D o...
Domain generalization aims to learn knowledge invariant across different...
We propose a new approach, called self-motivated pyramid curriculum doma...
Existing domain adaptation methods generally assume different domains ha...