Published on Wed Aug 15 2018

Scene Coordinate Regression with Angle-Based Reprojection Loss for Camera Relocalization

Xiaotian Li, Juha Ylioinas, Jakob Verbeek, Juho Kannala

Image-based camera relocalization is an important problem in computer vision and robotics. Recent works utilize convolutional neural networks (CNNs) to retrieve 3D world coordinates.

0
0
0
Abstract

Image-based camera relocalization is an important problem in computer vision and robotics. Recent works utilize convolutional neural networks (CNNs) to regress for pixels in a query image their corresponding 3D world coordinates in the scene. The final pose is then solved via a RANSAC-based optimization scheme using the predicted coordinates. Usually, the CNN is trained with ground truth scene coordinates, but it has also been shown that the network can discover 3D scene geometry automatically by minimizing single-view reprojection loss. However, due to the deficiencies of the reprojection loss, the network needs to be carefully initialized. In this paper, we present a new angle-based reprojection loss, which resolves the issues of the original reprojection loss. With this new loss function, the network can be trained without careful initialization, and the system achieves more accurate results. The new loss also enables us to utilize available multi-view constraints, which further improve performance.

Sun Apr 02 2017
Computer Vision
Geometric Loss Functions for Camera Pose Regression with Deep Learning
PoseNet is a deep convolutional neural network which learns to regress the 6-DOF camera pose from a single image. It was trained using a naive loss function, with hyper-parameters which require expensive tuning.
0
0
0
Fri Feb 09 2018
Computer Vision
Full-Frame Scene Coordinate Regression for Image-Based Localization
Image-based localization, or camera relocalization, is a fundamental problem in computer vision and robotics. We propose to perform the scene coordinate regression in a full-frame manner to make the computation efficient at test time. We adopt a fully convolutional encoder-decoder neural network architecture.
0
0
0
Wed May 13 2020
Computer Vision
3D Scene Geometry-Aware Constraint for Camera Localization with Deep Learning
Camera localization is a fundamental and key component of autonomous driving vehicles and mobile robots to localize themselves globally. Recently end-to-end approaches based on convolutional neural network have been much studied to achieve or exceed 3D-geometry based traditional methods.
0
0
0
Fri Jan 04 2019
Computer Vision
Relative Geometry-Aware Siamese Neural Network for 6DOF Camera Relocalization
6DOF camera relocalization is an important component of autonomous driving and navigation. Deep learning has recently emerged as a promising technique to tackle this problem. We present a novel relative geometry-aware Siamese neural network.
0
0
0
Wed May 27 2015
Neural Networks
PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
PoseNet is a real-time monocular six degree of freedom relocalization system. It trains a convolutional neural network to Regress the 6-DOF camera pose from a single RGB image in an end-to-end manner with no need for engineering or optimisation.
0
0
0
Mon Jul 31 2017
Computer Vision
Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network
We propose a new deep learning based approach for camera relocalization. Our approach localizes a given query image by using a convolutional neural network for first retrieving similar database images and then predicting the relative pose between the query and the database images.
0
0
0