DuctTake: Spatiotemporal Video Compositing

TL;DR

DuctTake introduces a novel spatiotemporal video compositing system that uses motion-compensated 3D graph cuts to efficiently combine multiple takes into a seamless video, reducing manual effort.

Contribution

It presents a new method for video compositing that avoids complex object segmentation by optimizing spatiotemporal seams with 3D graph cuts, enhancing usability and performance.

Findings

Produces high-quality composites comparable to professional tools

Reduces creation time significantly

Operates efficiently on HD video in an interactive setting

Abstract

DuctTake is a system designed to enable practical compositing of multiple takes of a scene into a single video. Current industry solutions are based around object segmentation, a hard problem that requires extensive manual input and cleanup, making compositing an expensive part of the film-making process. Our method instead composites shots together by finding optimal spatiotemporal seams using motion-compensated 3D graph cuts through the video volume. We describe in detail the required components, decisions, and new techniques that together make a usable, interactive tool for compositing HD video, paying special attention to running time and performance of each section. We validate our approach by presenting a wide variety of examples and by comparing result quality and creation time to composites made by professional artists using current state-of-the-art tools.