Pre-recorded Sessions: From 4 December 2020 | Live Sessions: 10 – 13 December 2020

4 – 13 December 2020



  • Ultimate Supporter Ultimate Supporter
  • Ultimate Attendee Ultimate Attendee

Date: Sunday, December 13th
Time: 9:00am - 10:00am
Venue: Main Room

Abassin Sourou Fangbemi, Ubisoft China, China
Alexis Rolland, Ubisoft China, China

Abstract: With the objective of automating the creation of animations for wildlife, this project from Ubisoft China introduces a novel strategy for generating synthetic training data for 2D and 3D pose estimation of animals using keyframe animations. The machine learning models trained with this synthetic data are integrated into an end-to-end pipeline called ZooBuilder, that takes a video input of an animal in the wild and produces the corresponding 3D animation. With this approach, we produce motion capture-like data from videos that can be used to accelerate the workflow of animators.

Speaker(s) Bio:
Abassin Sourou Fangbemi is an Associate Data Scientist at Ubisoft China, AI & Data Lab. He obtained his doctorate degree in 2018 at the University of Science and Technology of China in Software Engineering, working on humans’ action recognition in videos. He received his master’s degree in 2014 and bachelor’s degree in 2011 at the same university, respectively in Media Management and Computer Science. He is interested in Machine Learning and Computer Vision, their application in the video games industry, and he is currently focusing his research on 2D and 3D pose estimation of animals from images and videos

Alexis Rolland has more than 10 years of experience in Information Technologies and Big Data. He has been working in the video games industry at Ubisoft for the last 9 years, where he most notably developed its Enterprise Data Platform. Since 2018, he has been managing Ubisoft China, AI & Data Lab with a mission of innovation, to accelerate the adoption of Machine Learning into game production pipelines and players experiences.