Cascaded Refinement Network for Point Cloud Completion

Abstract

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.

CVPR2020

References in corpus (4)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
• Deep Level Sets: Implicit Surface Representations for 3D Shape Inference

Cited by in corpus (3)

• CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers
• KTNet: Knowledge Transfer for Unpaired 3D Shape Completion
• Consistent Two-Flow Network for Tele-Registration of Point Clouds