Recent breakthroughs in geometric Deep Learning (DL) and the availabilit...
Accurate, robust, and real-time LiDAR-based odometry (LO) is imperative ...
The volume of space debris currently orbiting the Earth is reaching an
u...
Deploying deep learning neural networks on edge devices, to accomplish t...
In recent years, deep learning (DL) has shown great potential in the fie...
Estimating the pose of an uncooperative spacecraft is an important compu...
3D scanning as a technique to digitize objects in reality and create the...
Visual place recognition is a key to unlocking spatial navigation for
an...
To automatically localize a target object in an image is crucial for man...
In this paper, a discriminator-free adversarial-based Unsupervised Domai...
This paper proposes an adaptive graph-based approach for multi-label ima...
Unsupervised anomaly detection in time-series has been extensively
inves...
Deep neural networks (DNNs) are typically optimized using various forms ...
3D reverse engineering is a long sought-after, yet not completely achiev...
The use of Deep Learning (DL) algorithms has improved the performance of...
Reconstructing 3D human body shapes from 3D partial textured scans remai...
While end-to-end approaches have achieved state-of-the-art performance i...
In this paper, we propose a new deep learning-based approach for
disenta...
Being capable of estimating the pose of uncooperative objects in space h...
Face identification/recognition has significantly advanced over the past...
This paper proposes the SPARK dataset as a new unique space object
multi...
We propose a Point-Voxel DeConvolution (PVDeConv) module for 3D data
aut...
The SHApe Recovery from Partial textured 3D scans challenge, SHARP 2020,...
We propose 3DBooSTeR, a novel method to recover a textured 3D body mesh ...
In this paper, we propose 3DBodyTex.Pose, a dataset that addresses the t...
This paper extends the Spatial-Temporal Graph Convolutional Network (ST-...
Complete and textured 3D reconstruction of dynamic scenes has been
facil...
The Dense Trajectories concept is one of the most successful approaches ...
3D data is a valuable asset in the field of computer vision as it provid...
In recent years, social media has played an increasingly important role ...