Completed
Quantitative Results
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Deep Network for Integrated 3D Sensing of Multiple People in Natural Images
Automatically move to the next video in the Classroom when playback concludes
- 1 Problem: Human Localization and Grouping
- 2 Objective
- 3 Approach: Find the Skeletal Joints
- 4 Ground Truth: Panoptic Studio
- 5 Computational Pipeline
- 6 Deep Volume Encoding (2d/3d)
- 7 Limb Scoring
- 8 3d Pose Decoding and Shape Estimati
- 9 Given the feature volume of a person and it's skeleton
- 10 SMPL: A Skinned Multi-Person Linear Model
- 11 Deep Autoencoder
- 12 Analysis of learning
- 13 Quantitative Results
- 14 CMU Panoptic dataset
- 15 Qualitative Results
