We present a new convolutional neural network, called Multi Voxel-Point Neurons Convolution (MVPConv), for fast and accurate 3D deep learning. The previous works adopt either individual point-based features or local-neighboring voxel-based features to process 3D model, which limits the performance of models due to the inefficient computation. Moreover, most of the existing 3D deep learning frameworks aim at solving one specific task, and only a few of them can handle a variety of tasks. Integrating both the advantages of the voxel and point-based methods, the proposed MVPConv can effectively increase the neighboring collection between point-based features and also promote the independence among voxel-based features. Simply replacing the corresponding convolution module with MVPConv, we show that MVPConv can fit in different backbones to solve a wide range of 3D tasks. Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MVPConv improves the accuracy of the backbone (PointNet) by up to 36%, and achieves higher accuracy than the voxel-based model with up to 34 times speedup. In addition, MVPConv also outperforms the state-of-the-art point-based models with up to 8 times speedup. Notably, our MVPConv achieves better accuracy than the newest point-voxel-based model PVCNN (a model more efficient than PointNet) with lower latency.
翻译:我们提出了一个新的革命神经网络,称为多式Voxel-Pod Neuros Convolution(MVPConv),用于快速和准确的3D深层学习。先前的工程采用单个点基特征或以本地邻接式Voxel为基础的特性,用于处理3D模型,这限制了模型的性能。此外,大多数现有的3D深层学习框架都旨在解决一项具体任务,而且其中只有少数几个能够处理各种任务。结合了 voxel 和点基方法的优势,拟议的MVP Conv可以有效地增加点基特征之间的相邻收集,同时促进Voxel基于特征的独立。简单地用MVP ConvConv取代相应的组合模块,因为计算效率不高。此外,MVP ConvCon(MVP Conv-Conv-Conferation)可以在不同的基准数据集(例如 ShapeNet Part Party, S3DIS和KITTI) 方面进行的广泛实验表明,MVP Conv-prol(P commational-commal-comm)通过36到更高的速度,也比NVIC-mod-x-x-x-x-x-x-x-xx-x-x-xxxx-x-xx-xxxxxxxxx-时间更近更近好。