# Wish You Were Here: Context-Aware Human Generation

arXiv: https://arxiv.org/abs/2005.10663 · HTML: https://mlsanity.com/paper/2005.10663/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2020.

## Built on by (most cited first, 10 of 10)

- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection](https://mlsanity.com/paper/2112.08935/) (2021)
- [Image Manipulation Detection by Multi-View Multi-Scale Supervision](https://mlsanity.com/paper/2104.06832/) (2021)
- [FlexIT: Towards Flexible Semantic Image Translation](https://mlsanity.com/paper/2203.04705/) (2022)
- [PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering](https://mlsanity.com/paper/2403.05053/) (2024)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [Multi-scale Attention Guided Pose Transfer](https://mlsanity.com/paper/2202.06777/) (2022)
- [Scene Aware Person Image Generation through Global Contextual Conditioning](https://mlsanity.com/paper/2206.02717/) (2022)
- [Semantically Consistent Person Image Generation](https://mlsanity.com/paper/2302.14728/) (2023)

## Abstract (arXiv)

We present a novel method for inserting objects, specifically humans, into existing images, such that they blend in a photorealistic manner, while respecting the semantic context of the scene. Our method involves three subnetworks: the first generates the semantic map of the new person, given the pose of the other persons in the scene and an optional bounding box specification. The second network renders the pixels of the novel person and its blending mask, based on specifications in the form of multiple appearance components. A third network refines the generated face in order to match those of the target person. Our experiments present convincing high-resolution outputs in this novel and challenging application domain. In addition, the three networks are evaluated individually, demonstrating for example, state of the art results in pose transfer benchmarks.