# Semantically Consistent Person Image Generation

## TL;DR

This paper introduces a data-driven, multi-step method for generating realistic, semantically coherent person images that seamlessly blend into complex scenes by conditioning on scene context and appearance attributes.

## Contribution

It presents a novel three-step approach combining semantic mask inference, representation selection, and appearance transfer for context-aware person image generation.

## Key findings

- Produces realistic person images that blend into scenes
- Maintains semantic consistency with existing scene elements
- Outperforms baseline methods in qualitative and quantitative evaluations

## Abstract

We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and appearance of the generated person are semantically conditioned on the existing persons in the scene. The proposed technique is divided into three sequential steps. At first, we employ a Pix2PixHD model to infer a coarse semantic mask that represents the new person's spatial location, scale, and potential pose. Next, we use a data-centric approach to select the closest representation from a precomputed cluster of fine semantic masks. Finally, we adopt a multi-scale, attention-guided architecture to transfer the appearance attributes from an exemplar image. The proposed strategy enables us to synthesize semantically coherent realistic persons that can blend into an existing scene without altering the global context. We conclude our findings with relevant qualitative and quantitative evaluations.