The robustness of SLAM algorithms in challenging environmental condition...
Spatial convolutions are extensively used in numerous deep video models....
Accurately predicting interactive road agents' future trajectories and
p...
We present a neural point cloud rendering pipeline through a novel
multi...
The learning and aggregation of multi-scale features are essential in
em...
Precision robotic manipulation tasks (insertion, screwing, precisely pic...
Recent work in computer vision and cognitive reasoning has given rise to...
Spatial convolutions are widely used in numerous deep video models. It
f...
Recent work in cognitive reasoning and computer vision has engendered an...
The central idea of contrastive learning is to discriminate between diff...
Deep learning technique has yielded significant improvements in point cl...
This technical report analyzes an egocentric video action detection meth...
With the recent surge in the research of vision transformers, they have
...
Exploiting multi-scale features has shown great potential in tackling
se...
Point clouds are often sparse and incomplete, which imposes difficulties...
In view of the difficulty in reconstructing object details in point clou...
We present a novel learning approach to recover the 6D poses and sizes o...
In recent years, self-supervised methods for monocular depth estimation ...
Point clouds are often sparse and incomplete. Existing shape completion
...
Accurate 6D object pose estimation is fundamental to robotic manipulatio...
Target detection and tracking provides crucial information for motion
pl...