ToFNest: Efficient normal estimation for time-of-flight depth cameras

In this work, we propose an efficient normal estimation method for depth images acquired by Time-of-Flight (ToF) cameras based on feature pyramid networks (FPN). We perform the normal estimation starting from the 2D depth images, projecting the measured data into the 3D space and computing the loss...

Full description

Saved in:
Bibliographic Details
Main Authors: Molnar, Szilard, Kelenyi, Benjamin, Tamas, Levente
Format: Conference Proceeding
Language:English
Subjects:
Cameras
Codes
Computer vision
Conferences
Estimation
Runtime
Three-dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we propose an efficient normal estimation method for depth images acquired by Time-of-Flight (ToF) cameras based on feature pyramid networks (FPN). We perform the normal estimation starting from the 2D depth images, projecting the measured data into the 3D space and computing the loss function for the point cloud normal. Despite its simplicity, our method called ToFNest proves to be efficient in terms of robustness and runtime. In order to validate ToFNest we performed extensive evaluations using both public and custom outdoor datasets. Compared with the state of the art methods, our algorithm is faster by an order of magnitude without losing precision on public datasets. The demo code is available on https://github.com/molnarszilard/ToFNest
ISSN:2473-9944
DOI:10.1109/ICCVW54120.2021.00205