PQDT：用于鲁棒点云修复的伪查询双 Transformer
PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration
提出伪查询模块与 Transformer 骨干网络，将几何变换分解为两阶段协同过程，为点云修复提供统一框架，可复用于其他 3D 感知任务中的退化数据处理。
原文依据 We propose a unified 3D restoration network that directly takes point clouds as input and adaptively reconstructs high-quality geometry under diverse degradation scenarios.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论点云是计算机视觉中一种基础的三维表示，支撑着广泛的感知任务。然而，现实世界中的点云常常因传感器限制或遮挡而遭受不完整性、噪声、离群点和不规则密度等退化。从这类退化数据中恢复干净且细节丰富的形状对下游应用至关重要。尽管现有的基于学习的方法在补全或去噪等单项任务上取得了进展，但它们通常依赖全局瓶颈特征，这会丢失细粒度几何信息，并且对变化的输入质量保持敏感。我们提出了一种统一的 3D 修复网络，直接以点云为输入，并在多种退化场景下自适应地重建高质量几何。我们方法的核心是一个伪查询模块，在 Transformer 骨干网络中实现，它将几何变换重新表述为两个协同阶段，以增强结构清晰度、鲁棒性和局部细节保持。在精心构建的基准上的大量实验表明，我们的方法在通用 3D 修复中超越了最优性能。它能有效处理补全、变形和去噪退化的复杂组合。通过这项工作，我们提供了一个新颖的、仅基于点云的统一骨干网络，用于鲁棒的 3D 修复，从而实现更通用的 3D 感知。
英文原文摘要 1403 字符
Point clouds are a fundamental 3D representation in computer vision, enabling a wide range of perception tasks. However, real-world point clouds often suffer from degradations such as incompleteness, noise, outliers, and irregular density, caused by sensor limitations or occlusions. Recovering clean and detailed shapes from such degraded data is crucial for downstream applications. While existing learning-based methods achieve progress on individual tasks like completion or denoising, they typically rely on global bottleneck features, which lose fine-grained geometry and remain sensitive to varying input quality. We propose a unified 3D restoration network that directly takes point clouds as input and adaptively reconstructs high-quality geometry under diverse degradation scenarios. At the core of our approach is a Pseudo-Query module, implemented within a Transformer backbone, which reformulates geometric translation into two cooperative stages to enhance structural clarity, robustness, and local detail preservation. Extensive experiments on curated benchmarks demonstrate that our approach surpasses state-of-the-art performance in general 3D restoration. It effectively handles complex combinations of completion, deformation, and denoising degradations. With this work, we provide a novel unified, point-only backbone for robust 3D restoration, enabling more versatile 3D perception.