Learning models on one labeled dataset that generalize well on another d...
Casting semantic segmentation of outdoor LiDAR point clouds as a 2D prob...
Semantic segmentation of point clouds in autonomous driving datasets req...
We propose a new self-supervised method for pre-training the backbone of...
It is of interest to localize a ground-based LiDAR point cloud on remote...
Segmenting or detecting objects in sparse Lidar point clouds are two
imp...
Most current neural networks for reconstructing surfaces from point clou...
Implicit neural networks have been successfully used for surface
reconst...
Large scale datasets created from crowdsourced labels or openly availabl...
There has been recently a growing interest for implicit shape
representa...
Rigid registration of point clouds with partial overlaps is a longstandi...
While there has been a number of studies on Zero-Shot Learning (ZSL) for...
The development of semi-supervised learning techniques is essential to
e...
We propose and study a method called FLOT that estimates scene flow on p...
We present a new lightweight CNN-based algorithm for multi-frame optical...
Recent state-of-the-art methods for point cloud semantic segmentation ar...
This paper is a technical report about our submission for the ECCV 2018 ...
In man-made environments such as indoor scenes, when point-based 3D
reco...
Understanding visual scenes relies more and more on dense pixel-wise
cla...
Large scale datasets created from user labels or openly available data h...
Point clouds are unstructured and unordered data, as opposed to images. ...
The Copernicus Sentinel-2 program now provides multispectral images at a...
This paper presents three fully convolutional neural network architectur...
Change detection is one of the main problems in remote sensing, and is
e...
Deep Residual Networks have reached the state of the art in many image
p...