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.
翻译:深层学习方法在 3D 语义分割中取得了显著的成功。然而,收集高密度附加注释的真实世界 3D 数据集是非常耗时和昂贵的。合成数据培训模型和对现实世界情景的概括化培训模式是一个令人感兴趣的替代方案,但不幸的是,却受到臭名昭著的域变换。在这项工作中,我们提议了一个数据导向域适应框架,以缓解不同遥感机制和跨域布局布局造成的模式和背景差距。我们的DODA包含虚拟扫描模拟,以模仿真实世界点云模式和尾尾部-水泡幼崽混合,以缩小以幼虫为基础的中间域的内部环境差距。关于3D室内语义分割的第一个不受监督的模拟到现实适应基准也建在3D-FRONAT、扫描网和S3DIS,以及7种流行的不受监督的Domae适应方法上。我们的DADA在 3D-FRONAT - > 扫描网和3D-FRONT - S3DIS。 代码可在 https://giuth/ABUB.C/DIS.C.