Completed
Experiment: Low Resolution Unsupervised Training
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Unsupervised Video Interpolation Using Cycle Consistency
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Overview
- 3 Frame Interpolation Techniques
- 4 Sparse Optical Flow
- 5 Common Frame Interpolation Implementation
- 6 Bi-directional flow-guided Interpolation
- 7 Super SloMo: Base Supervised Architecture
- 8 Limitations on the state-of-the-art
- 9 Unsupervised Video Interpolation
- 10 Unsupervised Interpolation
- 11 Cycle Consistency GAN
- 12 Cycle Consistency Cost Function
- 13 Time Domain Consistency Constraint
- 14 Pseudo Supervised Loss
- 15 Primary Objective Function
- 16 Final Training Loss Function
- 17 Dataset and Metrics
- 18 Experiment Setup: Datasets Used
- 19 Experiment Setup: Training
- 20 Evaluation Methods
- 21 Experiment: Low Resolution Unsupervised Training
- 22 Experiment: Domain Gap Testing
- 23 Experiment: Fine Tune Domain Transfer
- 24 Experiment: Qualitative Results
- 25 Ablation: Optimal Weights
- 26 Conclusion