Abstract
We introduce ROAR (Robust Object Removal and Re-annotation), a scalable framework for privacy-preserving dataset obfuscation that eliminates sensitive objects instead of modifying them. Our method integrates instance segmentation with generative inpainting to remove identifiable entities while preserving scene integrity. Extensive evaluations on 2D COCO-based object detection show that ROAR achieves 87.5% of the baseline detection average precision (AP), whereas image dropping achieves only 74.2% of the baseline AP, highlighting the advantage of scrubbing in preserving dataset utility. The degradation is even more severe for small objects due to occlusion and loss of fine-grained details. Furthermore, in NeRF-based 3D reconstruction, our method incurs a PSNR loss of at most 1.66 dB while maintaining SSIM and improving LPIPS, demonstrating superior perceptual quality. Our findings establish object removal as an effective privacy framework, achieving strong privacy guarantees with minimal performance trade-offs. The results highlight key challenges in generative inpainting, occlusion-robust segmentation, and task-specific scrubbing, setting the foundation for future advancements in privacy-preserving vision systems.
Abstract (translated)
我们介绍了ROAR（Robust Object Removal and Re-annotation），这是一个用于隐私保护的数据集模糊处理的可扩展框架，它通过消除敏感对象而不是修改它们来实现这一目标。我们的方法结合了实例分割和生成式填补技术，以去除可识别实体的同时保持场景完整性。在基于2D COCO的对象检测上的广泛评估表明，ROAR实现了基准检测平均精度（AP）的87.5%，相比之下，图像删除仅达到基准AP的74.2%，突显了擦除方法在保留数据集效用方面的优势。对于小对象来说，由于遮挡和细微特征丢失的问题，这种退化现象更为严重。 此外，在基于NeRF的3D重建中，我们的方法最多导致1.66 dB的PSNR损失，同时保持SSIM并提高LPIPS，展示了卓越的感知质量。我们的研究成果确立了物体移除作为有效的隐私框架的地位，实现了强有力的隐私保证，并在性能妥协方面达到最小化。结果突显了生成式填补、抗遮挡分割和任务特定擦除的关键挑战，为未来隐私保护视觉系统的进步奠定了基础。
URL
https://arxiv.org/abs/2504.16557
