Nowadays, robotics, AR, and 3D modeling applications attract considerabl...
In a multi-task learning (MTL) setting, a single model is trained to tac...
Recent advances in interactive segmentation (IS) allow speeding up and
s...
Most 3D instance segmentation methods exploit a bottom-up strategy, typi...
Recently, sparse 3D convolutions have changed 3D object detection. Perfo...
Processing large indoor scenes is a challenging task, as scan registrati...
Recently, promising applications in robotics and augmented reality have
...
In this paper, we introduce the task of multi-view RGB-based 3D object
d...
Recent works on click-based interactive segmentation have demonstrated
s...
Traffic sign recognition is a well-researched problem in computer vision...
Single-view depth estimation plays a crucial role in scene understanding...
In recent years generative models of visual data have made a great progr...
Image harmonization is an important step in photo editing to achieve vis...
Accurate depth map estimation is an essential step in scene spatial mapp...
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...
We present a novel method for image anomaly detection, where algorithms ...
Optical Flow (OF) and depth are commonly used for visual odometry since ...
Monocular Depth Estimation is an important problem of Computer Vision th...
Human gait or walking manner is a biometric feature that allows
identifi...