R-PGA：通过可重照明的3D高斯点散布实现鲁棒的物理对抗伪装生成
R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting
AI总结：
本文提出R-PGA框架，通过可重照明的3D高斯点散布技术，解决自动驾驶系统中对抗性伪装生成的鲁棒性问题，提升复杂动态场景下的泛化能力。
摘要：
物理对抗性伪装对自动驾驶系统构成严重安全威胁，通过将对抗性纹理映射到3D物体上。然而，当前方法在复杂动态场景中仍脆弱，无法在多样化的几何（例如视角配置）和辐射计量（例如动态光照、大气散射）变化中泛化。我们归因于模拟和优化中的两个根本限制。首先，对粗略、过于简化的模拟（例如通过CARLA）的依赖导致显著的领域差距，将优化限制在偏见的特征空间中。其次，针对平均性能的标准策略导致损失景观崎岖，使伪装容易受到配置变化的影响。为弥合这些差距，我们提出基于可重照明的3D高斯点散布（3DGS）的攻击框架（R-PGA）。技术上，为了解决模拟保真度问题，我们利用3DGS确保逼真重建，并将其与物理解耦的属性相结合，将内在材料与光照解耦。此外，我们设计了一个混合渲染管道，利用精确的可重照明3DGS进行前景渲染，同时使用预训练的图像翻译模型合成合理的重照明背景，使其与重照明前景对齐。为了解决优化鲁棒性问题，我们提出硬物理配置挖掘（HPCM）模块，旨在主动挖掘最坏的物理配置并抑制其对应的损失峰值。该策略不仅降低了总体损失幅度，还有效平滑了崎岖的损失景观，确保在不同物理配置下保持一致的对抗有效性和鲁棒性。
英文摘要：
Physical adversarial camouflage poses a severe security threat to autonomous driving systems by mapping adversarial textures onto 3D objects. Nevertheless, current methods remain brittle in complex dynamic scenarios, failing to generalize across diverse geometric (e.g., viewing configurations) and radiometric (e.g., dynamic illumination, atmospheric scattering) variations. We attribute this deficiency to two fundamental limitations in simulation and optimization. First, the reliance on coarse, oversimplified simulations (e.g., via CARLA) induces a significant domain gap, confining optimization to a biased feature space. Second, standard strategies targeting average performance result in a rugged loss landscape, leaving the camouflage vulnerable to configuration shifts.To bridge these gaps, we propose the Relightable Physical 3D Gaussian Splatting (3DGS) based Attack framework (R-PGA). Technically, to address the simulation fidelity issue, we leverage 3DGS to ensure photo-realistic reconstruction and augment it with physically disentangled attributes to decouple intrinsic material from lighting. Furthermore, we design a hybrid rendering pipeline that leverages precise Relightable 3DGS for foreground rendering, while employing a pre-trained image translation model to synthesize plausible relighted backgrounds that align with the relighted foreground.To address the optimization robustness issue, we propose the Hard Physical Configuration Mining (HPCM) module, designed to actively mine worst-case physical configurations and suppress their corresponding loss peaks. This strategy not only diminishes the overall loss magnitude but also effectively flattens the rugged loss landscape, ensuring consistent adversarial effectiveness and robustness across varying physical configurations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
