Continuity Editing for 3D Animation
Abstract: We describe an optimization-based approach for auto-matically creating well-edited movies from a 3D an-imation. While previous work has mostly focused on the problem of placing cameras to produce nice-looking views of the action, the problem of cutting and past-ing shots from all available cameras has never been ad-dressed extensively. In this paper, we review the main causes of editing errors in literature and propose an edit-ing model relying on a minimization of such errors. We make a plausible semi-Markov assumption, resulting in a dynamic programming solution which is computation-ally efficient. We also show that our method can gen-erate movies with different editing rhythms and vali-date the results through a user study. Combined with state-of-the-art cinematography, our approach therefore promises to significantly extend the expressiveness and naturalness of virtual movie-making.
Article: Download PDF
Video: Download Video
Presentation: Download PDF
For evaluation purposes, we are making our experimental data (including rushes and their annotations) and our experimental results publicly available. The soundtrack used is the property of Universal Pictures. The dataset is the property of INRIA and is distributed under a Creative Commons Licence CC-BY-NC-SA.
For researchers who want to use the dataset, please quote the paper as follows:
Quentin Galvane, Rémi Ronfard, Christophe Lino, Marc Christie. Continuity Editing for 3D Animation.
AAAI Conference on Artificial Intelligence, Austin, Texas. AAAI Press, Jan 2015.
Rushes: Videos and annotations
– Contains the rushes of the 25 cameras used in this paper with their annotations.
Project: Unity project
– Unity project containing the scene, the animations and the camera used in this paper
WebPlayer: Click here to try it !
– Explore the scene and see the 25 cameras