Unsupervised Metric Relocalization Using Transform Consistency Loss

11/01/2020
by   Mike Kasper, et al.
0

Training networks to perform metric relocalization traditionally requires accurate image correspondences. In practice, these are obtained by restricting domain coverage, employing additional sensors, or capturing large multi-view datasets. We instead propose a self-supervised solution, which exploits a key insight: localizing a query image within a map should yield the same absolute pose, regardless of the reference image used for registration. Guided by this intuition, we derive a novel transform consistency loss. Using this loss function, we train a deep neural network to infer dense feature and saliency maps to perform robust metric relocalization in dynamic environments. We evaluate our framework on synthetic and real-world data, showing our approach outperforms other supervised methods when a limited amount of ground-truth information is available.

READ FULL TEXT

page 2

page 7

page 8

research
04/30/2020

M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network

The present MVS methods with deep learning have an impressive performanc...
research
11/30/2022

Self-Supervised Feature Learning for Long-Term Metric Visual Localization

Visual localization is the task of estimating camera pose in a known sce...
research
05/07/2019

Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency

We present a learning based approach for multi-view stereopsis (MVS). Wh...
research
04/05/2022

SNUG: Self-Supervised Neural Dynamic Garments

We present a self-supervised method to learn dynamic 3D deformations of ...
research
11/16/2022

Self-supervised Egomotion and Depth Learning via Bi-directional Coarse-to-Fine Scale Recovery

Self-supervised learning of egomotion and depth has recently attracted g...
research
05/10/2021

ICON: Learning Regular Maps Through Inverse Consistency

Learning maps between data samples is fundamental. Applications range fr...
research
06/19/2018

Unsupervised Deep Multi-focus Image Fusion

Convolutional neural networks have recently been used for multi-focus im...

Please sign up or login with your details

Forgot password? Click here to reset