论文标题
用于点云完成的级联精炼网络
Cascaded Refinement Network for Point Cloud Completion
论文作者
论文摘要
点云通常是稀疏和不完整的。现有的形状完成方法无法生成对象的详细信息或学习复杂点分布。为此，我们提出了一个级联的改进网络以及粗到精细的策略，以综合详细的对象形状。考虑到具有全局形状信息的部分输入的本地细节，我们可以将现有细节保存在不完整的点集中，并以高保真度生成缺失的零件。我们还设计了一个补丁判别器，该贴片歧视器保证每个地方都具有相同的模式与地面真相，以学习复杂的点分布。不同数据集上的定量和定性实验表明，与3D点云完成任务上现有的最新方法相比，我们的方法取得了优越的结果。我们的源代码可从https://github.com/xiaogangw/cascaded-point-completion.git获得。
Point clouds are often sparse and incomplete. Existing shape completion methods are incapable of generating details of objects or learning the complex point distributions. To this end, we propose a cascaded refinement network together with a coarse-to-fine strategy to synthesize the detailed object shapes. Considering the local details of partial input with the global shape information together, we can preserve the existing details in the incomplete point set and generate the missing parts with high fidelity. We also design a patch discriminator that guarantees every local area has the same pattern with the ground truth to learn the complicated point distribution. Quantitative and qualitative experiments on different datasets show that our method achieves superior results compared to existing state-of-the-art approaches on the 3D point cloud completion task. Our source code is available at https://github.com/xiaogangw/cascaded-point-completion.git.
