arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.08392cs.CV
收藏

三维点云实例分割的动态卷积方法

Dynamic Convolution for 3D Point Cloud Instance Segmentation

The University of Adelaide(阿德莱德大学);Zhejiang University(浙江大学)

Tong He, Chunhua Shen, Anton van den Hengel

摘要:

提出了一种基于动态卷积的三维点云实例分割方法。这使它能够适应,在推理,以不同的功能和对象的规模。这样做避免了自自底向上的方法的一些陷阱,包括依赖于超参数调整和启发式后处理管道来补偿对象大小的不可避免的变化,即使在单个场景中。通过收集具有相同语义类别和几何质心投票接近的同质点,极大地提高了网络的表示能力。然后,通过几个简单的卷积层解码,其中参数是根据输入生成的。所提出的方法是无命题的,而是利用一个卷积过程,适应每个实例的空间和语义特征。一个轻量级的Transformer,建立在瓶颈层上,允许模型捕获长距离的依赖关系,而计算开销有限。其结果是一种简单,高效,强大的方法,在各种数据集上产生强大的性能:ScanNetV2,S3DIS和PartNet。基于体素和基于点的架构上的一致改进意味着所提出的方法的有效性。代码可在:https://git.io/DyCo3D

英文摘要:

We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. This enables it to adapt, at inference, to varying feature and object scales. Doing so avoids some pitfalls of bottom up approaches, including a dependence on hyper-parameter tuning and heuristic post-processing pipelines to compensate for the inevitable variability in object sizes, even within a single scene. The representation capability of the network is greatly improved by gathering homogeneous points that have identical semantic categories and close votes for the geometric centroids. Instances are then decoded via several simple convolution layers, where the parameters are generated conditioned on the input. The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance. A light-weight transformer, built on the bottleneck layer, allows the model to capture long-range dependencies, with limited computational overhead. The result is a simple, efficient, and robust approach that yields strong performance on various datasets: ScanNetV2, S3DIS, and PartNet. The consistent improvements on both voxel- and point-based architectures imply the effectiveness of the proposed method. Code is available at: https://git.io/DyCo3D

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑