PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation
PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation
复制标题
DOI：
10.1111/cgf.14601
复制
发表时间：
2021-12
影响因子：
2.5
通讯作者：
Gopal Sharma;Bidya Dash;Aruni RoyChowdhury;Matheus Gadelha;Marios Loizou;Liangliang Cao;Rui Wang;E. Learned-Miller;Subhransu Maji;E. Kalogerakis
中科院分区：
文献类型：
--
作者：
Gopal Sharma;Bidya Dash;Aruni RoyChowdhury;Matheus Gadelha;Marios Loizou;Liangliang Cao;Rui Wang;E. Learned-Miller;Subhransu Maji;E. Kalogerakis
我们提出了PriFit，这是一种用于3D点云分割网络的标签有效学习的半监督方法。PriFit将几何图元拟合与基于点的表示学习相结合。它的核心思想是学习点表示，其聚类揭示了可以很好地近似基本几何图元（如长方体和椭圆体）的形状区域。然后，学习的点表示可以在现有的网络架构中重新使用，用于3D点云分割，并提高其在少数镜头设置中的性能。根据我们对广泛使用的ShapeNet和PartNet基准测试的实验，PriFit在这种情况下优于几种最先进的方法，这表明可分解为原语是学习预测语义部分的表示的有用先验。我们提出了一些烧蚀实验不同的几何图元和下游任务的选择，以证明该方法的有效性。
We present PriFit, a semi‐supervised approach for label‐efficient learning of 3D point cloud segmentation networks. PriFit combines geometric primitive fitting with point‐based representation learning. Its key idea is to learn point representations whose clustering reveals shape regions that can be approximated well by basic geometric primitives, such as cuboids and ellipsoids. The learned point representations can then be re‐used in existing network architectures for 3D point cloud segmentation, and improves their performance in the few‐shot setting. According to our experiments on the widely used ShapeNet and PartNet benchmarks, PriFit outperforms several state‐of‐the‐art methods in this setting, suggesting that decomposability into primitives is a useful prior for learning representations predictive of semantic parts. We present a number of ablative experiments varying the choice of geometric primitives and downstream tasks to demonstrate the effectiveness of the method.