NewEvery arXiv paper, its researchers & institutions — mapped.
computer vision

Unconstrained Foreground Object Search

arXiv:1908.03675

summary

The paper introduces an unconstrained foreground object search method that encodes background images and candidate foreground objects in a shared latent space, enabling efficient retrieval of diverse objects for image editing without class restrictions.

Abstract

Many people search for foreground objects to use when editing images. While existing methods can retrieve candidates to aid in this, they are constrained to returning objects that belong to a pre-specified semantic class. We instead propose a novel problem of unconstrained foreground object (UFO) search and introduce a solution that supports efficient search by encoding the background image in the same latent space as the candidate foreground objects. A key contribution of our work is a cost-free, scalable approach for creating a large-scale training dataset with a variety of foreground objects of differing semantic categories per image location. Quantitative and human-perception experiments with two diverse datasets demonstrate the advantage of our UFO search solution over related baselines.

To appear in ICCV 2019

Topics & keywords

#foreground object retrieval#image editing#latent space embedding#large-scale dataset creation#visual searchunconstrained foreground object searchlatent space encodingscalable training datasetimage compositionretrieval baseline