deep-camera-relocalization icon indicating copy to clipboard operation
deep-camera-relocalization copied to clipboard

Published 20 hours ago • verified publisher icon futurely
→

Metadata

VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization, Geometric loss functions for camera pose regression with deep learning, PoseNet: A Convolutional Network for Real-Time 6-DOF C...

Deep Camera Relocalization

Getting Started

  • Download the Cambridge Landmarks King's College dataset from here.

  • Download the starting and trained weights from here.

  • To run:

    • Extract the King's College dataset to wherever you prefer
    • Extract the starting and trained weights to wherever you prefer
    • If you want to retrain, simply run train.py
    • If you just want to test, simply run test.py

References

Ronald Clark, Sen Wang, Andrew Markham, Niki Trigoni, Hongkai Wen. VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization. CVPR 2017.

Alex Kendall and Roberto Cipolla. Geometric loss functions for camera pose regression with deep learning. CVPR, 2017.

Alex Kendall, Matthew Grimes and Roberto Cipolla. PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization. ICCV, 2015.

Acknowledgement

Original implementation of PoseNet: https://github.com/kentsommer/tensorflow-posenet

← Metadata

86
Stars
30
Forks
Watchers

Owner

verified publisher icon futurely

Metadata

VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization, Geometric loss functions for camera pose regression with deep learning, PoseNet: A Convolutional Network for Real-Time 6-DOF C...

Back