We present an automated and efficient approach for retrieving high-quali...
In this work we introduce S-TREK, a novel local feature extractor that
c...
Rigid registration of point clouds is a fundamental problem in computer
...
We present an automatic method for annotating images of indoor scenes wi...
We propose a novel approach for deep learning-based Multi-View Stereo (M...
We propose an accurate and lightweight convolutional neural network for
...
Establishing a sparse set of keypoint correspon dences between images is...
We propose a novel method applicable in many scene understanding problem...
Most state-of-the-art instance segmentation methods produce binary
segme...
We present a novel deep-learning-based method for Multi-View Stereo. Our...
In this paper, we present a novel deep neural network architecture for j...
In this work, we introduce a novel, end-to-end trainable CNN-based
archi...
We propose a novel method for reconstructing floor plans from noisy 3D p...
We explore how a general AI algorithm can be used for 3D scene understan...
In this work, we propose BP-MVSNet, a convolutional neural network
(CNN)...
We propose a novel lightweight network for stereo estimation. Our networ...
We propose a machine learning based approach for automatic regularizatio...
In the fast developing countries it is hard to trace new buildings
const...
In this paper we present a method for building boundary refinement and
r...
We propose four novel solvers for estimating the relative pose of a
mult...
It has been proposed by many researchers that combining deep neural netw...
We present a novel method to reconstruct the 3D layout of a room –
walls...
In this paper we present four cases of minimal solutions for two-view
re...
Deep Neural Networks (DNNs) have the potential to improve the quality of...
We propose a simple yet effective method to learn to segment new indoor
...
We show that it is possible to learn semantic segmentation from very lim...
This paper addresses the highly challenging problem of automatically
det...
Automated toll systems rely on proper classification of the passing vehi...
While an increasing interest in deep models for single-image depth estim...
In this work, we propose a novel approach to prioritize the depth map
co...
Standing at the paradigm shift towards data-intensive science, machine
l...
In this paper we present a scalable approach for robustly computing a 3D...
Learned confidence measures gain increasing importance for outlier remov...