Description: PhD in Video Modelling of Natural Phenomena
We offer a fully funded PhD in the video modelling of natural phenomena. The idea is to automatically make three dimensional, dynamic, models of fires, smoke, water etc from video input. Such models will be editable so that brand new video can be made from them. The intention is to replace the physically based models currently used, which are expensive to build and very hard to use. Models from video are easier to acquire and easier to use, making them attractive to the games, films, and broadcast industries.
This project builds on the solid platform of our previous work on modelling trees , water , and more recently on tracking smoke  and segmentation of general phenomena . The aim is to develop a method for modelling smoke and fire for use in computer games. Follow the links at http://www.cs.bath.ac.uk/~pmh/OAK/Natural_Phenomena.html for example video.
The successful applicant will join a team of PhD students, post-docs and academic staff that make up the Visual Computing group at the University of Bath. The group has state of the art equipment for motion capture using camera, including a fully equipped green studio and a set of synchronised very high speed camera. The new PhD will be expected to contribute to the on-going tradition of publishing in the very highest quality forums across the world, and travel to deliver their papers to an international audience.
To learn more about this project, including a structured programme of study and it is value to industry contact the lead investigator Peter Hall on email@example.com.
 C. Li, Y-Z. Song, P.Willis, O. Deussen, P.Hall , Modeling and Generating Moving Trees from Video, ACM Transactions on Graphics 30(6) (SIGGRAPH Asia), 127:1-127:12, 2011.
 C. Li, D. Pickup, D. Marshall, D. Cosker, P.Willis, P.Hall, Single Video Based Water Surface Modeling. IEEE Transactions on Visualization and Computer Graphics, 19(7), 1241-1251, 2013.
 D. Chen, W. Li, P. Hall, Dense Motion Estimation for Smoke. ACCV 2016.
 D. Teney, D. Kitt, P. Hall, M. Brown. Learning Similarity Metrics for Dynamic Scene Segmentation. CVPR 2015.