The virtual cinematographer: a paradigm for automatic real-time camera control and directing
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Viewpoint Selection using Viewpoint Entropy
VMV '01 Proceedings of the Vision Modeling and Visualization Conference 2001
Artistic Composition for Image Creation
Proceedings of the 12th Eurographics Workshop on Rendering Techniques
Digital Cinematography & Directing
Digital Cinematography & Directing
Real-Time Cinematography for Games (Game Development Series)
Real-Time Cinematography for Games (Game Development Series)
ACM SIGGRAPH 2005 Papers
Dynamic View Selection for Time-Varying Volumes
IEEE Transactions on Visualization and Computer Graphics
Virtual world explorations by using topological and semantic knowledge
The Visual Computer: International Journal of Computer Graphics
Determination of camera parameters for character motions using motion area
The Visual Computer: International Journal of Computer Graphics
Motion overview of human actions
ACM SIGGRAPH Asia 2008 papers
Hi-index | 0.00 |
Camera control plays an important role in computer graphics for producing expressive images or animations. An appropriate viewing setting usually enhances the richness and quality of the generated results. In this paper, we propose an automatic method to determine the viewing parameters (e.g., camera position, camera distance) of motions based on the cinematography, artistic composition, and film editing rules. Our method addresses four main issues embedded in this problem: camera placement, shot determination, view selection of shot, and view refinement. For the first issue, based on cinematographic rules, we argue that character's vision and orientation as features, which are used to determine the number of cameras and their positions. For the second issue, we propose a motion segmentation method to convert a sequence into motion cuts, which represent the shots of the motion. For the third issue, a view selection algorithm based on visibility measure is devised to select an appropriate camera (view). For the fourth issue, we finalize the camera parameters by considering type of shot, common visual axis, and artistic composition. Comparing to fixed-view shots, our results convey more information by providing viewers with better visual appeal and scene understanding.