TY - GEN
T1 - An Interactive System for Supporting Creative Exploration of Cinematic Composition Designs
AU - He, Rui
AU - Wei, Huaxin
AU - Cao, Ying
N1 - Publisher Copyright:
© 2024 Owner/Author.
PY - 2024/10/13
Y1 - 2024/10/13
N2 - Designing cinematic compositions, which involves moving cameras through a scene, is essential yet challenging in filmmaking. Machinima filmmaking provides real-time virtual environments for exploring different compositions flexibly and efficiently. However, producing high-quality cinematic compositions in such environments still requires significant cinematography skills and creativity. This paper presents Cinemassist , a tool designed to support and enhance this creative process by generating a variety of cinematic composition proposals at both keyframe and scene levels, which users can incorporate into their workflows and achieve more creative results. At the crux of our system is a deep generative model trained on real movie data, which can generate plausible, diverse camera poses conditioned on 3D animations and additional input semantics. Our model enables an interactive cinematic composition design workflow where users can co-design with the model by being inspired by model-generated suggestions while having control over the generation process. Our user study and expert rating find Cinemassist can facilitate the design process for users of different backgrounds and enhance the design quality especially for users with animation expertise, demonstrating its potential as an invaluable tool in the context of digital filmmaking.
AB - Designing cinematic compositions, which involves moving cameras through a scene, is essential yet challenging in filmmaking. Machinima filmmaking provides real-time virtual environments for exploring different compositions flexibly and efficiently. However, producing high-quality cinematic compositions in such environments still requires significant cinematography skills and creativity. This paper presents Cinemassist , a tool designed to support and enhance this creative process by generating a variety of cinematic composition proposals at both keyframe and scene levels, which users can incorporate into their workflows and achieve more creative results. At the crux of our system is a deep generative model trained on real movie data, which can generate plausible, diverse camera poses conditioned on 3D animations and additional input semantics. Our model enables an interactive cinematic composition design workflow where users can co-design with the model by being inspired by model-generated suggestions while having control over the generation process. Our user study and expert rating find Cinemassist can facilitate the design process for users of different backgrounds and enhance the design quality especially for users with animation expertise, demonstrating its potential as an invaluable tool in the context of digital filmmaking.
KW - Creativity Support Tool
KW - Digital Filmmaking
KW - Intelligent Cinematography
KW - Machine Learning
KW - Machinima
UR - http://www.scopus.com/inward/record.url?scp=85215125706&partnerID=8YFLogxK
U2 - 10.1145/3654777.3676393
DO - 10.1145/3654777.3676393
M3 - Conference article published in proceeding or book
AN - SCOPUS:85215125706
T3 - UIST 2024 - Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology
BT - UIST 2024 - Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology
PB - Association for Computing Machinery, Inc
T2 - 37th Annual ACM Symposium on User Interface Software and Technology, UIST 2024
Y2 - 13 October 2024 through 16 October 2024
ER -