Human Body Restoration with One-Step Diffusion Model and A New Benchmark

TL;DR

This paper introduces a new high-quality human image dataset and a novel one-step diffusion model called OSDHuman for human body restoration, demonstrating superior performance over existing methods.

Contribution

The study presents the creation of the PERSONA dataset using an automated pipeline and proposes OSDHuman, a one-step diffusion model with a high-fidelity embedder for improved human image restoration.

Findings

OSDHuman outperforms existing methods in visual quality.

The PERSONA dataset surpasses other human datasets in quality and content.

The HFIE prompt generator effectively guides the diffusion model.

Abstract

Human body restoration, as a specific application of image restoration, is widely applied in practice and plays a vital role across diverse fields. However, thorough research remains difficult, particularly due to the lack of benchmark datasets. In this study, we propose a high-quality dataset automated cropping and filtering (HQ-ACF) pipeline. This pipeline leverages existing object detection datasets and other unlabeled images to automatically crop and filter high-quality human images. Using this pipeline, we constructed a person-based restoration with sophisticated objects and natural activities (\emph{PERSONA}) dataset, which includes training, validation, and test sets. The dataset significantly surpasses other human-related datasets in both quality and content richness. Finally, we propose \emph{OSDHuman}, a novel one-step diffusion model for human body restoration. Specifically, we propose a high-fidelity image embedder (HFIE) as the prompt generator to better guide the model with low-quality human image information, effectively avoiding misleading prompts. Experimental results show that OSDHuman outperforms existing methods in both visual quality and quantitative metrics. The dataset and code will at https://github.com/gobunu/OSDHuman.