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