activity
20192022
most citedNeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields

6 citations · 7 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV20226 cited

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…

cs.CV20221 cited

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…

cs.CV2021

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…

cs.RO2021

Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs

Antoni Rosinol, Andrew Violette, Marcus Abate +5

Humans are able to form a complex mental model of the environment they move in. This mental model captures geometric and semantic aspects of the scene, describes the environment at…

cs.CV2020

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…

cs.RO2020

3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans

Antoni Rosinol, Arjun Gupta, Marcus Abate +2

We present a unified representation for actionable spatial perception: 3D Dynamic Scene Graphs. Scene graphs are directed graphs where nodes represent entities in the scene (e.g. o…