Wish You Were Here: Context-Aware Human Generation

TL;DR

This paper introduces a three-network system for photorealistically inserting humans into images, maintaining scene semantics and appearance consistency, with high-resolution outputs and state-of-the-art pose transfer performance.

Contribution

The novel three-network architecture enables realistic human insertion into images, combining semantic mapping, appearance rendering, and face refinement, advancing the field of image editing.

Findings

High-resolution, realistic human insertion demonstrated

Networks achieve state-of-the-art results in pose transfer benchmarks

Method effectively blends inserted humans with scene context

Abstract

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.