47 citations · 66 across the 9 of their papers we have counts for
5 papers · 1 filter
NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields
Antoni Rosinol, John J. Leonard, Luca Carlone
We propose a novel geometric and photometric 3D mapping pipeline for accurate and real-time scene reconstruction from monocular images. To achieve this, we leverage recent advances…
Probabilistic Volumetric Fusion for Dense Monocular SLAM
Antoni Rosinol, John J. Leonard, Luca Carlone
We present a novel method to reconstruct 3D scenes from images by leveraging deep dense monocular SLAM and fast uncertainty propagation. The proposed approach is able to 3D reconst…
Smooth Mesh Estimation from Depth Data using Non-Smooth Convex Optimization
Antoni Rosinol, Luca Carlone
Meshes are commonly used as 3D maps since they encode the topology of the scene while being lightweight. Unfortunately, 3D meshes are mathematically difficult to handle directly be…
Primal-Dual Mesh Convolutional Neural Networks
Francesco Milano, Antonio Loquercio, Antoni Rosinol +2
Recent works in geometric deep learning have introduced neural networks that allow performing inference tasks on three-dimensional geometric data by defining convolution, and somet…
Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities
Antoni Rosinol, Torsten Sattler, Marc Pollefeys +1
Visual-Inertial Odometry (VIO) algorithms typically rely on a point cloud representation of the scene that does not model the topology of the environment. A 3D mesh instead offers…