UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation

TL;DR

UnitedHuman introduces an end-to-end framework that leverages multi-source, multi-resolution datasets to improve high-resolution human image generation, effectively addressing local detail synthesis issues.

Contribution

The paper proposes a novel Multi-Source Spatial Transformer and a continuous GAN framework to align and utilize diverse datasets for enhanced human image synthesis.

Findings

Achieves higher quality human images than holistic dataset methods

Effectively aligns multi-source images with a human model

Demonstrates superior performance through extensive experiments

Abstract

Human generation has achieved significant progress. Nonetheless, existing methods still struggle to synthesize specific regions such as faces and hands. We argue that the main reason is rooted in the training data. A holistic human dataset inevitably has insufficient and low-resolution information on local parts. Therefore, we propose to use multi-source datasets with various resolution images to jointly learn a high-resolution human generative model. However, multi-source data inherently a) contains different parts that do not spatially align into a coherent human, and b) comes with different scales. To tackle these challenges, we propose an end-to-end framework, UnitedHuman, that empowers continuous GAN with the ability to effectively utilize multi-source data for high-resolution human generation. Specifically, 1) we design a Multi-Source Spatial Transformer that spatially aligns multi-source images to full-body space with a human parametric model. 2) Next, a continuous GAN is proposed with global-structural guidance and CutMix consistency. Patches from different datasets are then sampled and transformed to supervise the training of this scale-invariant generative model. Extensive experiments demonstrate that our model jointly learned from multi-source data achieves superior quality than those learned from a holistic dataset.