In recent studies, the generalization of neural radiance fields for nove...
Robust estimation is a crucial and still challenging task, which involve...
Point clouds are naturally sparse, while image pixels are dense. The
inc...
Robot localization using a previously built map is essential for a varie...
Although point cloud registration has achieved remarkable advances in
ob...
3D scene flow characterizes how the points at the current time flow to t...
Promising complementarity exists between the texture features of color i...
Scene flow represents the 3D motion of each point in the scene, which
ex...
In the existing methods, LiDAR odometry shows superior performance, but
...
3D scene flow estimation from point clouds is a low-level 3D motion
perc...
Scene flow represents the motion of points in the 3D space, which is the...
Multiple object tracking (MOT) is a significant task in achieving autono...
3D Multi-Object Tracking (MOT) is an important part of the unmanned vehi...
Depth and ego-motion estimations are essential for the localization and
...
An efficient 3D point cloud learning architecture, named PWCLO-Net, for ...
Scene flow estimation is the task to predict the point-wise 3D displacem...
Optical flow estimation is a fundamental problem of computer vision and ...
Real-time 3D human pose estimation is crucial for human-computer interac...
A new unsupervised learning method of depth and ego-motion using multipl...
Recently, learning based methods for the robot perception from the image...
A novel 3D point cloud learning model for deep LiDAR odometry, named
PWC...
The semantic segmentation of point clouds is an important part of the
en...
Application of Deep Reinforcement Learning (DRL) algorithms in real-worl...
Scene flow represents the 3D motion of every point in the dynamic
enviro...
In autonomous driving, monocular sequences contain lots of information.
...
Convolutional neural networks (CNN) have made significant advances in
hy...