3D Pose Detection using Densepose: Dense Human Pose Estimation In The Wild by FAIR and INRIA

Description:

Human pose estimation is another fundamental problem in computer vision. Computer’s ability to recognize and understand humans in images and videos is crucial for multiple tasks including autonomous driving, action recognition, human-computer interaction, augmented reality and robotics vision. Advances in 3D human pose estimation remain limited because obtaining ground-truth information on the dense correspondence, depth, motion, body-part segmentation, occlusions is a very challenging task. In this talk, I plan to cover the following topics:

1. Introduction to what is pose estimation problem
2. A small demo of how the output looks like
3. Areas of Application
4. What is in the wild, UV coordinates, how is 2D (openpose) different from 3D pose estimation and it's need
5. Introduction to Dense-Pose COCO dataset
6. Quick intro of Mask RCNN
7. Improvements from the past
8. Evaluation metrics used

This talk will provide an introduction to pose estimation problem, DensePose, and its's applications motivating the audience to use it in their projects.

Prerequisites:

1. Proficiency in the Python programming language
   2. Basics of neural networks
   3. Knowledge of mask-RCNN, SMPL, SURREAL

Content URLs:

1. Slides: https://docs.google.com/presentation/d/1oRKcHQaSLwV_Afe4S9jY0Zc-WtBi93iKwcaHTteRzT4/edit?usp=sharing
   2. Research Paper: https://arxiv.org/abs/1802.00434
   3. Complentary material: http://densepose.org
   4. Research Paper (Mask-RCNN): https://arxiv.org/abs/1703.06870
   5. Code: https://github.com/facebookresearch/DensePose
   6. Demo of the network: https://www.youtube.com/watch?v=Dhkd_bAwwMc

Speaker Info:

Shreya Chawla is a senior year B.Tech. computer science and engineering graduate student. She has experience working on deep learning, computer vision, machine learning, natural language processing, and speech processing and synthesis. She has interned at CSIR-CDRI labs as a data science intern and is undergoing an internship at IIIT - H as a research intern. As a part of CSI, Cybros, and DSC clubs in her college, she encourages and guides fellow students to use Python language and explore its vastness. She has mentored teams to work on technologies like recommender system and computer vision based Python projects. She actively takes part in hackathons around her. In her free time, she watches TV series and listens to music.

Speaker Links:

1. LinkedIn: https://www.linkedin.com/in/shreyachawla1998/
   2. Github: https://github.com/shreya888/