Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body

TL;DR

This paper introduces FHAD, a new task and datasets for detecting and repairing abnormal human body structures in generated images, and proposes HumanCalibrator, a framework that effectively identifies and repairs these abnormalities.

Contribution

The paper presents the FHAD task, constructs high-quality datasets, and proposes HumanCalibrator, a novel framework for abnormality detection and repair in human images.

Findings

High accuracy in abnormality detection

Effective repair of human body abnormalities

Preservation of original visual content

Abstract

Recent improvements in visual synthesis have significantly enhanced the depiction of generated human photos, which are pivotal due to their wide applicability and demand. Nonetheless, the existing text-to-image or text-to-video models often generate low-quality human photos that might differ considerably from real-world body structures, referred to as "abnormal human bodies". Such abnormalities, typically deemed unacceptable, pose considerable challenges in the detection and repair of them within human photos. These challenges require precise abnormality recognition capabilities, which entail pinpointing both the location and the abnormality type. Intuitively, Visual Language Models (VLMs) that have obtained remarkable performance on various visual tasks are quite suitable for this task. However, their performance on abnormality detection in human photos is quite poor. Hence, it is quite important to highlight this task for the research community. In this paper, we first introduce a simple yet challenging task, i.e., \textbf{F}ine-grained \textbf{H}uman-body \textbf{A}bnormality \textbf{D}etection \textbf{(FHAD)}, and construct two high-quality datasets for evaluation. Then, we propose a meticulous framework, named HumanCalibrator, which identifies and repairs abnormalities in human body structures while preserving the other content. Experiments indicate that our HumanCalibrator achieves high accuracy in abnormality detection and accomplishes an increase in visual comparisons while preserving the other visual content.