Learning the Depths of Moving People by Watching Frozen People

Learning the Depths of Moving People by Watching Frozen People

Launchpad via YouTube Direct link

Intro

1 of 21

1 of 21

Intro

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Learning the Depths of Moving People by Watching Frozen People

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Goal
  3. 3 Where Could We Use This?
  4. 4 Existing Technologies
  5. 5 SLAM/MVS
  6. 6 Traditional Stereo Triangulation
  7. 7 Triangulation Here... Not So Good!
  8. 8 Single View Depth Prediction Using Multi-View Supervision
  9. 9 Internet Images Into Data
  10. 10 After Applying MV...
  11. 11 Depth Prediction on MegaDepth... A Lot Less Noisy!
  12. 12 Statues vs People
  13. 13 Mannequin Challenge
  14. 14 Training Data... Now On People
  15. 15 Get The Training Data
  16. 16 Train The Model (Using RGB- Only)
  17. 17 Prediction on Single RGB Image
  18. 18 More The Input Better The Performance
  19. 19 Getting Pseudo-Depth Map
  20. 20 Final Model Output
  21. 21 Application

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.