Course Information

• When: Wednesday, July 26th

• Where: TBD

• When: TBD (AM only)

• Schedule:

  • 8:45 - 8:55 Introduction [all]

  • 8:55 - 9:40 Feature-based Place Recognition [Akihiko Torii]

  • 9:40 - 10:25 Learning-based Place Recognition [Giorgos Tolias]

  • 10:25 - 10:45 Coffee Break

  • 10:45 - 11:30 Feature-based Visual Localization [Torsten Sattler]

  • 11:30 - 12:15 Learning-based Visual Localization [Alex Kendall]

  • 12:15 - 12:30 Panel discussion: The future of Place Recognition and Visual Localization [all]

Materials

Slides

• Introduction [video]

• Place Recognition

  • Feature-based [video]

  • Learning-based [video]

• Visual Localization

  • Feature-based [video]

  • Learning-based [video]

Code pointers

• Place Recognition

  • Feature-based

    • DenseVLAD

    • DisLocation

    • Place recognition with repetitive structures

  • Learning-based

    • NetVLAD

    • R-MAC and Integral Max pooling

    • CNN Image Retrieval Learns from BoW (siamese embedding learning)

    • Diffusion based search

• Visual Localization

  • Feature-based

    • kd-tree baseline, Vocabulary-based Prioritized Search (VPS), Active Search

    • 3D model compression

    • Geometric burstiness weighting for image retrieval

    • iOS demo for local pose tracking via SLAM

  • Learning-based

    • PoseNet

    • Differentiable RANSAC

Datasets

• 7 Scenes (Visual Localization)

• Aachen (Visual Localization)

• Cambridge Landmarks (Visual Localization)

• Dubrovnik, Rome (Visual Localization)

• San Francisco SF-0, reference poses (Visual Localization)

• Aachen Day-Night and RobotCar Seasons datasets (Visual Localization) (dataset available upon request)

• Training images for CNN image retrieval

• TUM LSI Dataset (Visual Localization)

Previous Tutorials

• CVPR 2014 Tutorial on Large-Scale Visual Place Recognition and Image-Based Localization

• CVPR 2015 Tutorial on Large-Scale Visual Place Recognition and Image-Based Localization