# Unconstrained Foreground Object Search

arXiv: https://arxiv.org/abs/1908.03675 · HTML: https://mlsanity.com/paper/1908.03675/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2019.

## Built on by (most cited first, 4 of 4)

- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Foreground Object Search by Distilling Composite Image Feature](https://mlsanity.com/paper/2308.04990/) (2023)
- [GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing](https://mlsanity.com/paper/2204.00125/) (2022)
- [PartStickers: Generating Parts of Objects for Rapid Prototyping](https://mlsanity.com/paper/2504.05508/) (2025)

## Abstract (arXiv)

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.