Omnimatte: Associating Objects and Their Effects in Video

TL;DR

This paper introduces a self-supervised method to automatically associate objects in videos with their related scene effects, such as reflections and smoke, enhancing scene understanding and editing capabilities.

Contribution

It proposes a novel approach to generate omnimattes that include objects and their effects without manual labels, applicable to diverse objects and effects in videos.

Findings

Successfully produces omnimattes for various objects and effects

Works on real-world videos with complex interactions

Operates in a self-supervised manner without manual annotations

Abstract

Computer vision is increasingly effective at segmenting objects in images and videos; however, scene effects related to the objects -- shadows, reflections, generated smoke, etc -- are typically overlooked. Identifying such scene effects and associating them with the objects producing them is important for improving our fundamental understanding of visual scenes, and can also assist a variety of applications such as removing, duplicating, or enhancing objects in video. In this work, we take a step towards solving this novel problem of automatically associating objects with their effects in video. Given an ordinary video and a rough segmentation mask over time of one or more subjects of interest, we estimate an omnimatte for each subject -- an alpha matte and color image that includes the subject along with all its related time-varying scene elements. Our model is trained only on the input video in a self-supervised manner, without any manual labels, and is generic -- it produces omnimattes automatically for arbitrary objects and a variety of effects. We show results on real-world videos containing interactions between different types of subjects (cars, animals, people) and complex effects, ranging from semi-transparent elements such as smoke and reflections, to fully opaque effects such as objects attached to the subject.