Where and Who? Automatic Semantic-Aware Person Composition

TL;DR

This paper presents an automated, semantic-aware person compositing method that selects and transforms human segments from a large database to generate realistic composite images based solely on a background image.

Contribution

It introduces a novel CNN model that predicts person locations and retrieves compatible human segments, advancing automated image compositing techniques.

Findings

Generated composites are visually convincing.

Model effectively predicts person locations from backgrounds.

Demonstrates potential for automated content creation.

Abstract

Image compositing is a method used to generate realistic yet fake imagery by inserting contents from one image to another. Previous work in compositing has focused on improving appearance compatibility of a user selected foreground segment and a background image (i.e. color and illumination consistency). In this work, we instead develop a fully automated compositing model that additionally learns to select and transform compatible foreground segments from a large collection given only an input image background. To simplify the task, we restrict our problem by focusing on human instance composition, because human segments exhibit strong correlations with their background and because of the availability of large annotated data. We develop a novel branching Convolutional Neural Network (CNN) that jointly predicts candidate person locations given a background image. We then use pre-trained deep feature representations to retrieve person instances from a large segment database. Experimental results show that our model can generate composite images that look visually convincing. We also develop a user interface to demonstrate the potential application of our method.