120 likes | 124 Views
SceneMaker: Automatic Visualisation of Screenplays. School of Computing & Intelligent Systems Faculty of Computing & Engineering University of Ulster, Magee, Northern Ireland hanser-e@email.ulster.ac.uk, {p.mckevitt, tf.lunney, j.condell}@ulster.ac.uk. Eva Hanser Prof. Paul Mc Kevitt
E N D
SceneMaker:Automatic Visualisation of Screenplays School of Computing & Intelligent Systems Faculty of Computing & Engineering University of Ulster, Magee, Northern Ireland hanser-e@email.ulster.ac.uk, {p.mckevitt, tf.lunney, j.condell}@ulster.ac.uk Eva Hanser Prof. Paul Mc Kevitt Dr. Tom Lunney Dr. Joan Condell
SCENEMAKER OVERVIEW • Automatically generate animated scenes from screenplays
AIMS : AIMS & OBJECTIVES • Realistic visualisation of emotional aspects • Well-designed representation through 3D animation, speech, audio and cinematography • Enhance believability of virtual actors and scene presentation Input: SceneMaker System Screen- play Output: Animation
OBJECTIVES : AIMS & OBJECTIVES • Inferencing emotions and semantic information within story context • Common sense, affective and cinematic knowledge reflecting human cognitive reasoning • Automatic genre recognition from text • Design, implementation and evaluation of SceneMaker
SEMANTIC TEXT PROCESSING : RELATED PROJECTS INT. M.I.T. HALLWAY -- NIGHT Lambeau and Tom come around a corner. His P.O.V. reveals a figure in silhouette blazing through the proof on the chalkboard. There is a mop and a bucket beside him. As Lambeau draws closer, reveal that the figure is Will, in his janitor's uniform. There is a look of intense concentration in his eyes. LAMBEAU Excuse me! WILL Oh, I'm sorry. LAMBEAU What're you doing? WILL (walking away) I'm sorry. • Standardized format and language of screenplays • Automatic access to information on location, timing, props, actors, events, manners, dialogue and camera direction (Jhala 2008) Screenplay Extract from ‘Good Will Hunting (1997)’
MODELLING EMOTIONAL BEHAVIOUR : RELATED PROJECTS • Reflecting emotions in automatic physical transformation of 3D models • Manner influences intensity, scale, force, fluency and timing of an action Greta (Pelachaud 2005) Personality & Emotion Engine(Su et al. 2007)
VISUALISING 3D SCENES : RELATED PROJECTS • WordsEye – Scene composition(Coyne & Sproat 2001) • ScriptViz – Screenplay visualisation(Liu & Leung 2006) • CONFUCIUS – Action & speech animation(Ma 2006) • CAMEO – Cinematic and genre visualisation(Shim & Kang 2008) ScriptViz CONFUCIUS CAMEO WordsEye
Screen-play Genre Multimedia Generation Text & Language Processing } } Script Editor Emotion Animation Player Context Interpretation Action ARCHITECTURE OF SCENEMAKER : DESIGN AND IMPLEMENTATION
GENRE IDENTIFICATION : DESIGN AND IMPLEMENTATION Emotion Module Tagged Film Script Gate Script Element Ontology Film Script WordNet-Affect Tokenizer .xml Concept Net .txt Part-Of-Speech MotionContent Film Pace Gazetteer Dialogue Length Sentence Splitter Most Dominant Emotions Genre Relevant Locations Genre Location Ontology WordNet KEA Key-phrase Extractor Training corpora Location key-phrases Genre Relevant Lighting Genre Light Ontology Controlled Indexing Training corpora Light key-phrases Free Indexing Theme Genre DirectorNotation (Film Ontology)
EVALUATION OF SCENEMAKER : DESIGN AND IMPLEMENTATION
SUMMARY SceneMaker • Heightens expressiveness, naturalness and artistic quality of computer generated animations • Assists crew on set – directors, actors, camera men, ... – drama students, script writers and advertising agencies • Mobile user interface for immediate use on set or anywhere • Animations manually editable