It would be so great and helpful to hear some opinions from someone as a professional in this field! The questions are as follows:
1) What are the barriers of real-time facial expression tracking system based on 2D data?
2) What are the advantages and disadvantages of facial expression capture based on 3D data (with depth camera or other techniques)?
3) In the long term, what facial motion capture method/company do you think the most highly of and why?
4) Which human body model (skeleton-based model, contour-based model, volume-based model) do you think will most probably become the mainstream model in the future?
5) What do you think of the top-down approach and bottom-up approach to Human Pose Estimation? What method/approach do you think is the most suitable for facial expression capture specifically?
Let's have an open discussion guys! Please feel free to share any of your thoughts or throw more questions on facial motion capture. Thanks a lot in advance for sharing your thoughts and time! Much appreciated!