Human Synthesis and Scene Compositing

TL;DR

This paper introduces HUSC, a comprehensive framework for realistic human image synthesis and scene compositing that leverages 3D reasoning to control appearance, pose, and scene integration, achieving state-of-the-art results.

Contribution

HUSC is the first framework to combine 3D reasoning with human synthesis and scene compositing for realistic, controllable human image generation in diverse scenes.

Findings

Achieves state-of-the-art synthesis scores on DeepFashion dataset.

Effectively models perspective, occlusion, and scene semantics.

Produces seamless human-scene composites with minimal artifacts.

Abstract

Generating good quality and geometrically plausible synthetic images of humans with the ability to control appearance, pose and shape parameters, has become increasingly important for a variety of tasks ranging from photo editing, fashion virtual try-on, to special effects and image compression. In this paper, we propose HUSC, a HUman Synthesis and Scene Compositing framework for the realistic synthesis of humans with different appearance, in novel poses and scenes. Central to our formulation is 3d reasoning for both people and scenes, in order to produce realistic collages, by correctly modeling perspective effects and occlusion, by taking into account scene semantics and by adequately handling relative scales. Conceptually our framework consists of three components: (1) a human image synthesis model with controllable pose and appearance, based on a parametric representation, (2) a person insertion procedure that leverages the geometry and semantics of the 3d scene, and (3) an appearance compositing process to create a seamless blending between the colors of the scene and the generated human image, and avoid visual artifacts. The performance of our framework is supported by both qualitative and quantitative results, in particular state-of-the art synthesis scores for the DeepFashion dataset.