论文标题
点变压器
Point Transformer
论文作者
论文摘要
自我发挥的网络已彻底改变了自然语言处理，并在图像分析任务（例如图像分类和对象检测）方面取得了令人印象深刻的进步。受这一成功的启发，我们研究了自我发项网络在3D点云处理中的应用。我们为点云设计自发层，并使用这些层来构建自我发挥的网络，以进行语义场景分割，对象部分分割和对象分类等任务。我们的Point Transformer设计在跨域和任务的先前工作中改善了。例如，在针对大型语义场景细分的具有挑战性的S3DIS数据集上，点变压器在区域5上达到70.4％的MIOU，以优于最强的先前模型，超过3.3个绝对百分比，并首先超过70％MIOU阈值。
Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detection. Inspired by this success, we investigate the application of self-attention networks to 3D point cloud processing. We design self-attention layers for point clouds and use these to construct self-attention networks for tasks such as semantic scene segmentation, object part segmentation, and object classification. Our Point Transformer design improves upon prior work across domains and tasks. For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70.4% on Area 5, outperforming the strongest prior model by 3.3 absolute percentage points and crossing the 70% mIoU threshold for the first time.
