Deep learning applications on LiDAR data suffer from a strong domain gap...
Many medical or pharmaceutical processes have strict guidelines regardin...
While transformer architectures have dominated computer vision in recent...
In order to ensure safe autonomous driving, precise information about th...
Many road accidents are caused by drowsiness of the driver. While there ...
Depth completion from sparse LiDAR and high-resolution RGB data is one o...
LiDAR depth maps provide environmental guidance in a variety of applicat...
Common domain shift problem formulations consider the integration of mul...
Large labeled data sets are one of the essential basics of modern deep
l...
In-the-wild human pose estimation has a huge potential for various field...
Interpolation of sparse pixel information towards a dense target resolut...
Scene flow is the dense 3D reconstruction of motion and geometry of a sc...
Dense pixel matching is required for many computer vision algorithms suc...
While short range 3D pedestrian detection is sufficient for emergency
br...
We present a test platform for visual in-cabin scene analysis and occupa...
We release SVIRO, a synthetic dataset for sceneries in the passenger
com...
We propose a new approach called LiDAR-Flow to robustly estimate a dense...
Running time of the light field depth estimation algorithms is typically...
Depth cameras are utilized in many applications. Recently light field
ap...
Most LiDAR odometry algorithms estimate the transformation between two
c...
Training a deep neural network is a non-trivial task. Not only the tunin...
In the last few years, convolutional neural networks (CNNs) have demonst...
Dense pixel matching is important for many computer vision tasks such as...
State-of-the-art scene flow algorithms pursue the conflicting targets of...
Scene flow describes the 3D position as well as the 3D motion of each pi...
Scene flow describes 3D motion in a 3D scene. It can either be modeled a...
Vehicles of higher automation levels require the creation of situation
a...
Optical Flow algorithms are of high importance for many applications.
Re...
Scene flow is a description of real world motion in 3D that contains mor...
While most scene flow methods use either variational optimization or a s...