vMAP: Vectorised Object Mapping for Neural Field SLAM

02/03/2023
by   Xin Kong, et al.
0

We present vMAP, an object-level dense SLAM system using neural field representations. Each object is represented by a small MLP, enabling efficient, watertight object modelling without the need for 3D priors. As an RGB-D camera browses a scene with no prior information, vMAP detects object instances on-the-fly, and dynamically adds them to its map. Specifically, thanks to the power of vectorised training, vMAP can optimise as many as 50 individual objects in a single scene, with an extremely efficient training speed of 5Hz map update. We experimentally demonstrate significantly improved scene-level and object-level reconstruction quality compared to prior neural field SLAM systems.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

research
11/21/2022

ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields

We present ESLAM, an efficient implicit neural representation method for...
research
03/23/2023

NEWTON: Neural View-Centric Mapping for On-the-Fly Large-Scale SLAM

Neural field-based 3D representations have recently been adopted in many...
research
07/23/2019

Deep-SLAM++: Object-level RGBD SLAM based on class-specific deep shape priors

In an effort to increase the capabilities of SLAM systems and produce ob...
research
08/25/2018

Fusion++: Volumetric Object-Level SLAM

We propose an online object-level SLAM system which builds a persistent ...
research
08/05/2021

Object-Augmented RGB-D SLAM for Wide-Disparity Relocalisation

We propose a novel object-augmented RGB-D SLAM system that is capable of...
research
09/15/2021

S3LAM: Structured Scene SLAM

We propose a new general SLAM system that uses the semantic segmentation...
research
04/09/2020

Where Does It End? – Reasoning About Hidden Surfaces by Object Intersection Constraints

Dynamic scene understanding is an essential capability in robotics and V...

Please sign up or login with your details

Forgot password? Click here to reset