Automatic Cinematography and Editing in Virtual Environments.

Abstract : The wide availability of high-resolution 3D models and the facility to create new geometrical and animated content, using low-cost input devices, open to many the possibility of becoming digital 3D storytellers. To date there is however a clear lack of accessible tools to easily create the cinematography (positioning and moving the cameras to create shots) and perform the editing of such stories (selecting appropriate cuts between the shots created by the cameras). Creating a movie requires the knowledge of a significant amount of empirical rules and established conventions. Most 3D animation packages do not encompass this expertise, calling the need for automatic approaches that would, at least partially, support users in their creative process. In this thesis we address both challenges of automating cinematography and editing in virtual environments.Using cameras to convey events and actions in dynamic environments is a major concern in many CG applications.In the context of crowd simulation, we present a novel approach to address the challenge of controlling multiple cameras tracking groups of targets. In this first contribution we propose a system that relies on Reynolds' model of steering behaviors to control and locally coordinate a collection of autonomous camera agents evolving in the dynamic 3D environments to shot multi-scale events.Editing a movie is a complex and tedious endeavor that requires a lot of expertise in the field. Therefore, automating the process calls for a formalization of this knowledge. Using continuity editing -- the predominant style of editing -- as a benchmark for evaluating edits, we introduce a novel optimization-based approach for automatically creating well-edited movies from a 3D animation. We propose an efficient solution through dynamic programming, by relying on a plausible semi-Markov assumption.Building upon our first contribution we then propose a novel importance-driven approach to cinematic replay that exploits both the narrative and geometric information in games to automatically compute camera paths. Combined with our editing framework, our solution generates coherent cinematic replays of game sessions.Finally, drawing inspiration from standard practices in the movie industry, we introduce a novel approach to camera path planning. This solution ensures realistic trajectories by constraining camera motion on a virtual rail. The camera position and orientation are optimized in time along the rail to best satisfy visual properties. The computed shots constitute relevant inputs for the editing framework which then generates compelling cinematographic content.
Complete list of metadatas

Cited literature [85 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01258572
Contributor : Abes Star <>
Submitted on : Tuesday, January 19, 2016 - 11:52:06 AM
Last modification on : Friday, June 22, 2018 - 5:04:57 PM
Long-term archiving on : Wednesday, April 20, 2016 - 11:22:18 AM

File

GALVANE_2015_archivage.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01258572, version 1

Collections

Citation

Quentin Galvane. Automatic Cinematography and Editing in Virtual Environments.. Artificial Intelligence [cs.AI]. Université Grenoble Alpes, 2015. English. ⟨NNT : 2015GREAM033⟩. ⟨tel-01258572⟩

Share

Metrics

Record views

1504

Files downloads

396