Video textures

TLDR

Video textures can replace static photos to add dynamic qualities and explicit actions. The paper develops video textures—a medium between photographs and videos—and presents methods for extracting structure from clips, synthesizing new videos, creating 3D textures via view morphing, and enabling user‑guided video‑based animation. Video textures produce a continuous, never‑exactly‑repeating stream of images, and the authors analyze clips to extract structure, synthesize new videos, extend to 3D through view morphing, and support interactive animation control. Applications include dynamic web scenes, special‑effects backdrops, games, and interactive video‑animation control.

Abstract

This paper introduces a new type of medium, called a video texture, which has qualities somewhere between those of a photograph and a video. A video texture provides a continuous infinitely varying stream of images. While the individual frames of a video texture may be repeated from time to time, the video sequence as a whole is never repeated exactly. Video textures can be used in place of digital photos to infuse a static image with dynamic qualities and explicit actions. We present techniques for analyzing a video clip to extract its structure, and for synthesizing a new, similar looking video of arbitrary length. We combine video textures with view morphing techniques to obtain 3D video textures. We also introduce video-based animation, in which the synthesis of video textures can be guided by a user through high-level interactive controls. Applications of video textures and their extensions include the display of dynamic scenes on web pages, the creation of dynamic backdrops for special effects and games, and the interactive control of video-based animation.