A Framework for Video-Driven Crowd Synthesis

TL;DR

This paper introduces a framework that synthesizes realistic 3D crowd animations from input videos by extracting motion patterns and simulating behaviors, with a new metric for visual similarity evaluation.

Contribution

It presents a novel video-driven crowd synthesis method that captures dominant motion paths and generates realistic 3D crowd animations with a new similarity metric.

Findings

Successfully synthesizes 3D crowds matching input video motions

Demonstrates effectiveness across different crowd scenarios

Provides a new metric for comparing crowd visual similarity

Abstract

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.