A Framework for Video-Driven Crowd Synthesis
This addresses the need for automated crowd synthesis in computer graphics and simulation, though it appears incremental as it builds on existing behavior-based frameworks.
The authors tackled the problem of generating realistic 3D crowd animations from input videos by extracting motion vectors to compute global paths and feeding them into a behavior-based simulation framework, resulting in synthesized crowds that match observed motion patterns with a new metric for visual similarity.
We present a framework for video-driven crowd synthesis. Motion vectors extracted from input crowd video are processed to compute global motion paths. These paths encode the dominant motions observed in the input video. These paths are then fed into a behavior-based crowd simulation framework, which is responsible for synthesizing crowd animations that respect the motion patterns observed in the video. Our system synthesizes 3D virtual crowds by animating virtual humans along the trajectories returned by the crowd simulation framework. We also propose a new metric for comparing the "visual similarity" between the synthesized crowd and exemplar crowd. We demonstrate the proposed approach on crowd videos collected under different settings.