CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction

04/11/2017
by   Keisuke Tateno, et al.
0

Given the recent advances in depth prediction from Convolutional Neural Networks (CNNs), this paper investigates how predicted depth maps from a deep neural network can be deployed for accurate and dense monocular reconstruction. We propose a method where CNN-predicted dense depth maps are naturally fused together with depth measurements obtained from direct monocular SLAM. Our fusion scheme privileges depth prediction in image locations where monocular SLAM approaches tend to fail, e.g. along low-textured regions, and vice-versa. We demonstrate the use of depth prediction for estimating the absolute scale of the reconstruction, hence overcoming one of the major limitations of monocular SLAM. Finally, we propose a framework to efficiently fuse semantic labels, obtained from a single frame, with dense SLAM, yielding semantically coherent scene reconstruction from a single view. Evaluation results on two benchmark datasets show the robustness and accuracy of our approach.

READ FULL TEXT

page 1

page 5

page 7

page 8

research
10/24/2022

NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields

We propose a novel geometric and photometric 3D mapping pipeline for acc...
research
06/07/2020

DeepRelativeFusion: Dense Monocular SLAM using Single-Image Relative Depth Prediction

Traditional monocular visual simultaneous localization and mapping (SLAM...
research
06/29/2019

SLAM Endoscopy enhanced by adversarial depth prediction

Medical endoscopy remains a challenging application for simultaneous loc...
research
04/01/2021

A Front-End for Dense Monocular SLAM using a Learned Outlier Mask Prior

Recent achievements in depth prediction from a single RGB image have pow...
research
07/25/2022

DeepFusion: Real-Time Dense 3D Reconstruction for Monocular SLAM using Single-View Depth and Gradient Predictions

While the keypoint-based maps created by sparse monocular simultaneous l...
research
04/22/2020

Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction

Classical monocular Simultaneous Localization And Mapping (SLAM) and the...
research
05/11/2018

Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors

We present "just-in-time reconstruction" as real-time image-guided inpai...

Please sign up or login with your details

Forgot password? Click here to reset