Animating Street View
This addresses the need for dynamic visualizations in urban planning or entertainment, but it appears incremental as it builds on existing techniques for scene reconstruction and simulation.
The paper tackles the problem of automatically animating street view imagery by populating it with naturally behaving pedestrians and vehicles, achieving this through scene reconstruction, behavior simulation, and rendering with consistent effects.
We present a system that automatically brings street view imagery to life by populating it with naturally behaving, animated pedestrians and vehicles. Our approach is to remove existing people and vehicles from the input image, insert moving objects with proper scale, angle, motion, and appearance, plan paths and traffic behavior, as well as render the scene with plausible occlusion and shadowing effects. The system achieves these by reconstructing the still image street scene, simulating crowd behavior, and rendering with consistent lighting, visibility, occlusions, and shadows. We demonstrate results on a diverse range of street scenes including regular still images and panoramas.