Animating virtual characters into immersive environments
Reference persons FABRIZIO LAMBERTI
External reference persons Alberto Cannav˛
Research Groups GR-09 - GRAphics and INtelligent Systems - GRAINS
Thesis type RESEARCH THESIS
Description Generating computer animations, particularly of virtual characters, is a very labor-intensive task, which requires animators to operate with sophisticated interfaces. Hence, researchers continuously experiment with alternative interaction paradigms that could possibly ease the above task. Among others, sketching represents a valid alternative to traditional interfaces since it can make interactions more expressive and intuitive. However, although the literature proposes several solutions leveraging sketch-based interfaces to solve different computer graphics challenges, generally these solutions are not fully integrated in the computer animation pipeline. Considering these aspects, an add-on for Blender was developed that combines the advantages offered by a sketch-based interface and of VR to let animators define poses and create virtual character animations in an immersive environment.
The objective of this thesis proposal (more than one student will be accepted) is to improve the usability of this VR-based sketching system by making use of machine learning algorithms able to support the following features:
(i) identifying the animation being created (expressed, e.g., with a sketch) and automatically generating the next/previous frames;
(ii) improving the results of the generated poses by leveraging a set of pre-defined character poses and armatures constraints;
(iii) implementing a recommendation system able to suggest a reconstructed/refined version of the sketches being drawn by the user for the sake of usability.
Cannav˛, A., Zhang, C., Wang, W., Lamberti, F. (2020, October). Posing 3D Characters in Virtual Reality Through In-the-Air Sketches. In International Conference on Computer Animation and Social Agents (pp. 51-61). Springer, Cham.
See also http://grains.polito.it/work.php
Deadline 06/03/2023 PROPONI LA TUA CANDIDATURA