用毫米波信号穿透遮挡，重建被遮住物体的完整3D形状。
Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completion
- 通过三阶段流程，将无线信号转化为3D几何结构。
- 在真实数据上实现72%召回率，精度保持85%。
- 无需真实标注数据，合成训练即可泛化到实际场景。
我们提出Wave-Former，一种可高精度重建完全遮挡、多样日常物体3D形状的新方法，有望推动机器人、增强现实和物流等领域发展。该方法利用毫米波（mmWave）无线信号，可穿透常见遮挡并反射自隐藏物体。与以往受限于覆盖范围小、噪声高的方法不同，Wave-Former引入物理感知的形状补全模型，以推断完整3D几何结构。其核心为创新的三阶段流程：生成候选几何面，采用专为mmWave信号设计的Transformer模型完成形状补全，最后通过熵引导选择最优表面。该方法仅需完全合成的点云数据进行训练，却在真实数据上表现优异。在与先进基线的对比中，召回率从54%提升至72%，同时保持85%的高精度。
原文摘要 · Abstract (English)
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%.
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。