
-
Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation
Domain adaptation is an important task to enable learning when labels ar...
read it
-
Rain rendering for evaluating and improving robustness to bad weather
Rain fills the atmosphere with water particles, which breaks the common ...
read it
-
LMSCNet: Lightweight Multiscale 3D Semantic Completion
We introduce a new approach for multiscale 3D semantic scene completion ...
read it
-
RGB-D-E: Event Camera Calibration for Fast 6-DOF Object Tracking
Augmented reality devices require multiple sensors to perform various ta...
read it
-
Model-based disentanglement of lens occlusions
With lens occlusions, naive image-to-image networks fail to learn an acc...
read it
-
xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Unsupervised Domain Adaptation (UDA) is crucial to tackle the lack of an...
read it
-
Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation
Image-to-image translation architectures may have limited effectiveness ...
read it
-
Physics-Based Rendering for Improving Robustness to Rain
To improve the robustness to rain, we present a physically-based rain re...
read it
-
3D Reconstruction of Deformable Revolving Object under Heavy Hand Interaction
We reconstruct 3D deformable object through time, in the context of a li...
read it
-
3D Surface Reconstruction from Voxel-based Lidar Data
To achieve fully autonomous navigation, vehicles need to compute an accu...
read it
-
Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation
Convolutional neural networks are designed for dense data, but vision da...
read it
-
A Statistical Update of Grid Representations from Range Sensors
In a wide range of robotic applications, being able to create a 3D model...
read it
-
End-to-End Race Driving with Deep Reinforcement Learning
We present research using the latest reinforcement learning algorithm fo...
read it