提出多模态框架REVIVE，修复自动驾驶车辆摄像头被涂鸦遮挡后的图像，提升感知可靠性。
REVIVE: A Multi-Modal Framework for Vandalism Detection and Recovery in Autonomous Vehicles
- 分步处理：先检测涂鸦攻击，再识别模式，最后用智能方法恢复图像
- 直接像素替换在匹配参考条件下可将目标检测召回率从0.588提至0.967
- 引入质量门控机制，确保恢复结果不劣于原始未修复画面，适合实际部署
自动驾驶车辆面临涂鸦导致的遮挡攻击（VOA），严重威胁基于摄像头的感知系统。现有检测框架虽能识别被篡改图像，但对物理遮挡后的图像恢复仍研究不足。本文提出恢复与增强被涂鸦图像以实现视觉卓越（REVIVE）框架，包含四步流程：(1) 二分类VOA检测，(2) 多类涂鸦模式识别，(3) 基于EfficientNet的U-Net分割，(4) 类型感知恢复——采用BLIP引导的Stable Diffusion、直接像素替换或自适应中值滤波。实验显示，不同涂鸦模式下，Stable Diffusion重建性能差异大（SSIM 0.667–0.867，PSNR 15.4–26.7dB），而匹配参考条件下的直接像素替换效果接近理想。在500对追踪的清洁/被涂鸦图像上，未恢复的VOA使YOLOv8l检测召回率降至0.588，而直接像素替换可恢复至0.967，F1-score达0.970。对比基线（LaMa、Telea、Navier-Stokes）虽提升图像相似性，但下游检测恢复有限。本研究将Stable Diffusion作为异步恢复分支，设置参考可用质量门控机制：无门控时，类型感知路由使每帧召回率降至0.304；有门控时，召回率回升至0.608，不低于未恢复基准，保证输出流始终优于或等同于原始未修复帧。REVIVE因此构建了一套结构化的自动驾驶车载涂鸦恢复框架。
原文摘要 · Abstract (English)
Autonomous vehicles (AVs) face increasing threats from vandalism-induced occlusion attacks (VOAs) that compromise camera-based perception. While detection frameworks can identify vandalized images, restoring camera-stream utility after physical occlusion remains underexplored. This paper presents present the Recovery and Enhancement of Vandalized Images for Vision Excellence (REVIVE) framework, a vandalism recovery pipeline integrating: (1) binary VOA detection, (2) multi-class VOA pattern identification, (3) EfficientNet-based U-Net segmentation, and (4) type-aware recovery using Bootstrapping Language-Image Pre-training (BLIP)-guided Stable Diffusion inpainting, direct pixel replacement, or adaptive median filtering. Stable Diffusion shows variable reconstruction performance (per-pattern SSIM 0.667-0.867, PSNR 15.4-26.7dB) across VOA patterns, while aligned direct pixel replacement achieves near-identical reconstruction under the aligned-reference condition. On 500 tracked clean/vandalized image pairs, unrecovered VOAs reduce YOLOv8l object-detection recall to 0.588, while direct pixel replacement restores recall to 0.967 and F1-score to 0.970 under that aligned-reference condition. LaMa, Telea, and Navier-Stokes baselines improve image similarity but provide more limited downstream detection recovery, and Stable Diffusion is treated as an asynchronous recovery branch subject to a quality gate rather than a blocking real-time perception step. We evaluate a reference-available quality gate that filters recovered candidates before downstream use: without it, type-aware routing degrades per-image recall to 0.304, whereas with it, recall returns to 0.608, at or above the unrecovered baseline, ensuring the forwarded stream is never worse than the unrecovered frame. REVIVE therefore, provides a structured recovery framework from VOAs in AVs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。