Wave-Former：基于无线形状补全的穿透遮挡三维重建
Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completion
把视觉中的形状补全范式迁移到毫米波点云上，用三阶段流水线（候选表面生成→Transformer 补全→熵引导选择）解决穿透遮挡后的稀疏高噪点云补全问题；其纯合成训练、真实数据泛化的设定，对做稀疏/噪声点云补全和跨域泛化的视觉研究者有直接借鉴价值。
原文依据 employs a transformer-based shape completion model designed specifically for mmWave signals
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 Wave-Former，一种能够对完全被遮挡的、多样化的日常物体进行高精度三维形状重建的新方法。该能力可开辟涵盖机器人、增强现实与物流的新应用。我们的方法利用毫米波（mmWave）无线信号，这类信号能够穿透常见遮挡物并从被遮挡物体上反射。与以往覆盖范围有限且噪声较大的毫米波重建方法不同，Wave-Former 引入了一个具备物理感知能力的形状补全模型，能够推断完整的三维几何。Wave-Former 设计的核心是一条新颖的三阶段流水线，它结合毫米波信号的物理特性，将原始无线信号与视觉形状补全的最新进展相衔接。该流水线首先提出候选几何表面，随后采用专为毫米波信号设计的基于 Transformer 的形状补全模型，最后执行熵引导的表面选择。这使得 Wave-Former 能够完全使用合成点云进行训练，同时对真实数据展现出令人印象深刻的泛化能力。在与最优基线的直接对比中，Wave-Former 将召回率从 54% 提升至 72%，同时保持 85% 的高精确率。
英文原文摘要 1281 字符
We present Wave-Former, a novel method capable of high-accuracy 3D shape reconstruction for completely occluded, diverse, everyday objects. This capability can open new applications spanning robotics, augmented reality, and logistics. Our approach leverages millimeter-wave (mmWave) wireless signals, which can penetrate common occlusions and reflect off hidden objects. In contrast to past mmWave reconstruction methods, which suffer from limited coverage and high noise, Wave-Former introduces a physics-aware shape completion model capable of inferring full 3D geometry. At the heart of Wave-Former's design is a novel three-stage pipeline which bridges raw wireless signals with recent advancements in vision-based shape completion by incorporating physical properties of mmWave signals. The pipeline proposes candidate geometric surfaces, employs a transformer-based shape completion model designed specifically for mmWave signals, and finally performs entropy-guided surface selection. This enables Wave-Former to be trained using entirely synthetic point-clouds, while demonstrating impressive generalization to real-world data. In head-to-head comparisons with state-of-the-art baselines, Wave-Former raises recall from 54% to 72% while maintaining a high precision of 85%.