NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping

10/18/2021
by   Stefan Lionar, et al.
0

We present a novel 3D mapping method leveraging the recent progress in neural implicit representation for 3D reconstruction. Most existing state-of-the-art neural implicit representation methods are limited to object-level reconstructions and can not incrementally perform updates given new data. In this work, we propose a fusion strategy and training pipeline to incrementally build and update neural implicit representations that enable the reconstruction of large scenes from sequential partial observations. By representing an arbitrarily sized scene as a grid of latent codes and performing updates directly in latent space, we show that incrementally built occupancy maps can be obtained in real-time even on a CPU. Compared to traditional approaches such as Truncated Signed Distance Fields (TSDFs), our map representation is significantly more robust in yielding a better scene completeness given noisy inputs. We demonstrate the performance of our approach in thorough experimental validation on real-world datasets with varying degrees of added pose noise.

READ FULL TEXT

page 7

page 8

research
04/03/2022

BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion

Dense 3D reconstruction from a stream of depth images is the key to many...
research
01/13/2020

RoutedFusion: Learning Real-time Depth Map Fusion

The efficient fusion of depth maps is a key part of most state-of-the-ar...
research
05/05/2022

ImPosIng: Implicit Pose Encoding for Efficient Camera Pose Estimation

We propose a novel learning-based formulation for camera pose estimation...
research
11/30/2020

NeuralFusion: Online Depth Fusion in Latent Space

We present a novel online depth map fusion approach that learns depth ma...
research
06/18/2023

Towards Real-time Scalable Dense Mapping using Robot-centric Implicit Representation

Real-time and high-quailty dense mapping is essential for robots to perf...
research
05/02/2022

POCD: Probabilistic Object-Level Change Detection and Volumetric Mapping in Semi-Static Scenes

Maintaining an up-to-date map to reflect recent changes in the scene is ...
research
11/25/2022

ToothInpaintor: Tooth Inpainting from Partial 3D Dental Model and 2D Panoramic Image

In orthodontic treatment, a full tooth model consisting of both the crow...

Please sign up or login with your details

Forgot password? Click here to reset