# What and Where: A Context-based Recommendation System for Object Insertion

arXiv: https://arxiv.org/abs/1811.09783 · HTML: https://mlsanity.com/paper/1811.09783/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2018.

## Built on by (most cited first, 14 of 14)

- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [OPA: Object Placement Assessment Dataset](https://mlsanity.com/paper/2107.01889/) (2021)
- [Learning Object Placement via Dual-path Graph Completion](https://mlsanity.com/paper/2207.11464/) (2022)
- [Thinking Outside the BBox: Unconstrained Generative Object Compositing](https://mlsanity.com/paper/2409.04559/) (2024)
- [Fast Object Placement Assessment](https://mlsanity.com/paper/2205.14280/) (2022)
- [Scene-aware Human Pose Generation using Transformer](https://mlsanity.com/paper/2308.02177/) (2023)
- [Deep Image Harmonization with Learnable Augmentation](https://mlsanity.com/paper/2308.00376/) (2023)
- [DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation](https://mlsanity.com/paper/2308.09972/) (2023)
- [DiffPop: Plausibility-Guided Object Placement Diffusion for Image Composition](https://mlsanity.com/paper/2406.07852/) (2024)
- [Spatial Transformation for Image Composition via Correspondence Learning](https://mlsanity.com/paper/2207.02398/) (2022)
- [Virtual Accessory Try-On via Keypoint Hallucination](https://mlsanity.com/paper/2310.17131/) (2023)
- [GraPLUS: Graph-based Placement Using Semantics for Image Composition](https://mlsanity.com/paper/2503.15761/) (2025)
- [HiddenObjects: Scalable Diffusion-Distilled Spatial Priors for Object Placement](https://mlsanity.com/paper/2604.10675/) (2026)
- [Hybrid Generative-Discriminative Object Placement](https://mlsanity.com/paper/2608.22692/) (2026)

## Abstract (arXiv)

In this work, we propose a novel topic consisting of two dual tasks: 1) given a scene, recommend objects to insert, 2) given an object category, retrieve suitable background scenes. A bounding box for the inserted object is predicted in both tasks, which helps downstream applications such as semi-automated advertising and video composition. The major challenge lies in the fact that the target object is neither present nor localized at test time, whereas available datasets only provide scenes with existing objects. To tackle this problem, we build an unsupervised algorithm based on object-level contexts, which explicitly models the joint probability distribution of object categories and bounding boxes with a Gaussian mixture model. Experiments on our newly annotated test set demonstrate that our system outperforms existing baselines on all subtasks, and do so under a unified framework. Our contribution promises future extensions and applications.