论文标题
DODA：面向数据的SIM到运行域适应3D语义分割
DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation
论文作者
论文摘要
深度学习方法在3D语义细分中取得了显着的成功。但是，收集密集注释的现实世界3D数据集非常耗时且昂贵。关于合成数据和对现实世界情景的推广的培训模型成为一种吸引人的选择，但不幸的是，臭名昭著的领域变化。在这项工作中，我们提出了一个面向数据的域适应性（DODA）框架，以减轻由不同的感应机制和跨域的布局放置引起的模式和上下文差距。我们的DODA涵盖了虚拟扫描模拟，以模仿现实世界中的点云图案和尾声的立方混合，以减轻基于立方体的中间域的内部上下文差距。 3D室内语义分割上的第一个无监督的SIM到运行适应基准也构建在3D-Front，Scannet和S3DIS上，以及7种流行的无监督域适应（UDA）方法。我们的DODA在3D -Front-> scannet和3d -Front-> S3DIS上都超过了13％的UDA方法。代码可在https://github.com/cvmi-lab/doda上找到。
Deep learning approaches achieve prominent success in 3D semantic segmentation. However, collecting densely annotated real-world 3D datasets is extremely time-consuming and expensive. Training models on synthetic data and generalizing on real-world scenarios becomes an appealing alternative, but unfortunately suffers from notorious domain shifts. In this work, we propose a Data-Oriented Domain Adaptation (DODA) framework to mitigate pattern and context gaps caused by different sensing mechanisms and layout placements across domains. Our DODA encompasses virtual scan simulation to imitate real-world point cloud patterns and tail-aware cuboid mixing to alleviate the interior context gap with a cuboid-based intermediate domain. The first unsupervised sim-to-real adaptation benchmark on 3D indoor semantic segmentation is also built on 3D-FRONT, ScanNet and S3DIS along with 7 popular Unsupervised Domain Adaptation (UDA) methods. Our DODA surpasses existing UDA approaches by over 13% on both 3D-FRONT -> ScanNet and 3D-FRONT -> S3DIS. Code is available at https://github.com/CVMI-Lab/DODA.
