Towards Scalable Human-aligned Benchmark for Text-guided Image Editing

TL;DR

HATIE introduces a comprehensive, automated benchmark for text-guided image editing that aligns well with human perception, enabling reliable evaluation across diverse editing tasks.

Contribution

We propose a large-scale, human-aligned benchmark with an automated evaluation pipeline for text-guided image editing, addressing the lack of standard evaluation methods.

Findings

HATIE's evaluation correlates strongly with human judgment.

Benchmark covers a wide range of editing tasks.

Provides insights into state-of-the-art model performance.

Abstract

A variety of text-guided image editing models have been proposed recently. However, there is no widely-accepted standard evaluation method mainly due to the subjective nature of the task, letting researchers rely on manual user study. To address this, we introduce a novel Human-Aligned benchmark for Text-guided Image Editing (HATIE). Providing a large-scale benchmark set covering a wide range of editing tasks, it allows reliable evaluation, not limited to specific easy-to-evaluate cases. Also, HATIE provides a fully-automated and omnidirectional evaluation pipeline. Particularly, we combine multiple scores measuring various aspects of editing so as to align with human perception. We empirically verify that the evaluation of HATIE is indeed human-aligned in various aspects, and provide benchmark results on several state-of-the-art models to provide deeper insights on their performance.