R3-PCQA：面向无参考三维点云质量评估的射线重投影强化方法
R3-PCQA: Ray-Reprojection-Reinforcement for No-Reference 3D Point Cloud Quality Assessment
将点云质量评估建模为多视角射线重投影加强化学习子云选择，可复用于任何需要从 2D 投影聚合 3D 结构感知的任务（如点云分割、配准中的视图聚合），其全局视图注意力聚合机制也可迁移到多视图特征融合。
原文依据 A geometric-aware ray-based reprojection pipeline simulates viewpoint-dependent observation of 3D structure.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的无参考三维点云质量评估方法大多将二维投影与三维点云视为相互独立的模态，并依赖简单的特征融合，因而忽略了人类三维感知的基本机制。为解决这一局限，本文提出 R3-PCQA（射线重投影强化三维点云质量评估器），一个新颖且有原理依据的框架，将感知先验显式编码进评估流程：几何感知的基于射线的重投影流程模拟对三维结构的视角相关观测；基于强化学习的质量显著子云选择器自适应地关注具有感知信息量的区域；全局视图注意力模块跨视角聚合局部质量响应，形成统一表征，从而支持可靠的跨视角推理。大量实验表明，R3-PCQA 在 SJTU-PCQA、WPC 和 WPC2.0 上取得了最优性能。
英文原文摘要 993 字符
Prevailing no-reference 3D point cloud quality assessment methods predominantly treat 2D projections and 3D point clouds as independent modalities and rely on simplistic feature fusion, thereby neglecting fundamental mechanisms underlying human 3D perception. To address this limitation, we introduce R3-PCQA (Ray-Reprojection-Reinforcement 3D Point Cloud Quality Assessor), a novel and principled framework that explicitly encodes perceptual priors into the assessment pipeline: A geometric-aware ray-based reprojection pipeline simulates viewpoint-dependent observation of 3D structure. A reinforcement-learning-based quality-salient subcloud selector adaptively attends to perceptually informative regions. The global view attention module aggregates local quality responses across viewpoints, forming a unified representation that facilitates reliable cross-view inference. Extensive experiments demonstrate that R3-PCQA achieves state-of-the-art performance on SJTU-PCQA, WPC, and WPC2.0.