Realtime Constraint-Based Cinematography for Complex Interactive 3D Worlds

Abstract

In 3D interactive ction systems, a virtual camera must \\ lm " the behaviors of multiple autonomous characters as they unpredictably interact with one another, are modi ed by the viewer, and manipulate artifacts in 3D worlds with complex scene geometries. It must continuously plan camera movements to clearly shoot the salient visual features of each relevant character. To address these issues, we have developed a 3D interactive ction system with a narrative planner that, together with a bank of autonomous character directors, creates cinematic goals for a constraintbased realtime 3D virtual cinematography planner. As interactive narratives unfold, a cinematic goal selector creates view constraints to lm the most salient activities performed by thecharacters. These constraints are then passed to a camera planner, which employs a partial constraintbased approach to compute the position and orientation of the virtual camera. This framework has been implemented in a prototype 3D interactive ction system, Cops&Robbers, a testbed with multiple characters interacting in an intricate cityscape.

Cite

Text

Bares et al. "Realtime Constraint-Based Cinematography for Complex Interactive 3D Worlds." AAAI Conference on Artificial Intelligence, 1998.

Markdown

[Bares et al. "Realtime Constraint-Based Cinematography for Complex Interactive 3D Worlds." AAAI Conference on Artificial Intelligence, 1998.](https://mlanthology.org/aaai/1998/bares1998aaai-realtime/)

BibTeX

@inproceedings{bares1998aaai-realtime,
  title     = {{Realtime Constraint-Based Cinematography for Complex Interactive 3D Worlds}},
  author    = {Bares, William H. and Grégoire, Joël P. and Lester, James C.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1998},
  pages     = {1101-1106},
  url       = {https://mlanthology.org/aaai/1998/bares1998aaai-realtime/}
}