The best way to combine the results of deep learning with standard 3D
re...
Volume rendering using neural fields has shown great promise in capturin...
Spatial memory, or the ability to remember and recall specific locations...
We introduce Ivy, a templated Deep Learning (DL) framework which abstrac...
Motion planning is a fundamental problem in robotics and machine percept...
Most realtime human pose estimation approaches are based on detecting jo...
In this paper, we show that the performance of a learnt generative model...
As Deep Learning continues to yield successful applications in Computer
...
In this paper, we present a novel end-to-end learning-based LiDAR
reloca...
The ability to estimate rich geometry and camera motion from monocular
i...
A trade-off exists between reconstruction quality and the prior
regulari...
We propose a novel, conceptually simple and general framework for instan...
Detailed 3D reconstruction is an important challenge with application to...
Variational Auto-encoders (VAEs) have been very successful as methods fo...
Sum-of-squares objective functions are very popular in computer vision
a...
Datasets have gained an enormous amount of popularity in the computer vi...
We propose an online object-level SLAM system which builds a persistent ...
The representation of geometry in real-time 3D perception systems contin...
This paper studies monocular visual odometry (VO) problem. Most of exist...
In this paper, we propose a novel 3D-RecGAN approach, which reconstructs...
Machine learning techniques, namely convolutional neural networks (CNN) ...
In this paper we present an on-manifold sequence-to-sequence learning
ap...