In recent years generative models of visual data have made a great progr...
Deep learning-based detectors usually produce a redundant set of object
...
Deep neural networks have become a mainstream approach to interactive
se...
Learning-based visual odometry and SLAM methods demonstrate a steady
imp...
Simultaneous localization and mapping (SLAM) is an essential component o...
We present a novel dataset for training and benchmarking semantic SLAM
m...
We present Adaptive Instance Selection network architecture for
class-ag...
Optical Flow (OF) and depth are commonly used for visual odometry since ...