RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection

TL;DR

This paper introduces RetouchingFFHQ, a large-scale, fine-grained face retouching dataset with over half a million images, enabling improved detection and analysis of various retouching types and levels.

Contribution

The creation of RetouchingFFHQ dataset with detailed retouching annotations and the development of a Multi-granularity Attention Module for enhanced detection performance.

Findings

Decent detection performance achieved on the new dataset.

Fine-grained retouching detection is feasible with the proposed methods.

The dataset enables future research in real-world face retouching detection.

Abstract

The widespread use of face retouching filters on short-video platforms has raised concerns about the authenticity of digital appearances and the impact of deceptive advertising. To address these issues, there is a pressing need to develop advanced face retouching techniques. However, the lack of large-scale and fine-grained face retouching datasets has been a major obstacle to progress in this field. In this paper, we introduce RetouchingFFHQ, a large-scale and fine-grained face retouching dataset that contains over half a million conditionally-retouched images. RetouchingFFHQ stands out from previous datasets due to its large scale, high quality, fine-grainedness, and customization. By including four typical types of face retouching operations and different retouching levels, we extend the binary face retouching detection into a fine-grained, multi-retouching type, and multi-retouching level estimation problem. Additionally, we propose a Multi-granularity Attention Module (MAM) as a plugin for CNN backbones for enhanced cross-scale representation learning. Extensive experiments using different baselines as well as our proposed method on RetouchingFFHQ show decent performance on face retouching detection. With the proposed new dataset, we believe there is great potential for future work to tackle the challenging problem of real-world fine-grained face retouching detection.