SVIA: A Street View Image Anonymization Framework for Self-Driving Applications

TL;DR

This paper introduces SVIA, a comprehensive framework for anonymizing street view images in self-driving applications, enhancing privacy by modifying sensitive regions while maintaining visual quality.

Contribution

The paper presents a novel three-component framework that extends image anonymization to street views, addressing privacy concerns specific to self-driving scenarios.

Findings

SVIA outperforms existing methods in privacy protection and image quality.

Experimental results show improved metrics on public datasets.

The framework effectively balances privacy and visual coherence.

Abstract

In recent years, there has been an increasing interest in image anonymization, particularly focusing on the de-identification of faces and individuals. However, for self-driving applications, merely de-identifying faces and individuals might not provide sufficient privacy protection since street views like vehicles and buildings can still disclose locations, trajectories, and other sensitive information. Therefore, it remains crucial to extend anonymization techniques to street view images to fully preserve the privacy of users, pedestrians, and vehicles. In this paper, we propose a Street View Image Anonymization (SVIA) framework for self-driving applications. The SVIA framework consists of three integral components: a semantic segmenter to segment an input image into functional regions, an inpainter to generate alternatives to privacy-sensitive regions, and a harmonizer to seamlessly stitch modified regions to guarantee visual coherence. Compared to existing methods, SVIA achieves a much better trade-off between image generation quality and privacy protection, as evidenced by experimental results for five common metrics on two widely used public datasets.