We introduce the task of open-vocabulary 3D instance segmentation.
Tradi...
During interactive segmentation, a model and a user work together to
del...
Segmenting humans in 3D indoor scenes has become increasingly important ...
We address 2D floorplan reconstruction from 3D scans. Existing approache...
Modern 3D semantic instance segmentation approaches predominantly rely o...
In this work, we present a new paradigm, called 4D-StOP, to tackle the t...
Current 3D segmentation methods heavily rely on large-scale point-cloud
...
We present Mix3D, a data augmentation technique for segmenting large-sca...
We propose a method to detect and reconstruct multiple 3D objects from a...
Inferring the pose and shape of vehicles in 3D from a movable platform s...
We propose DualConvMesh-Nets (DCM-Net) a family of deep hierarchical
con...
We present 3D-MPA, a method for instance segmentation on 3D point clouds...
In this work, we propose Dilated Point Convolutions (DPC) which drastica...
Recent deep learning models achieve impressive results on 3D scene analy...
In this paper, we present a deep learning architecture which addresses t...
Deep learning approaches have made tremendous progress in the field of
s...
Complementing images with inertial measurements has become one of the mo...