Skeleton-bridged Point Completion: From Global Inference to Local Adjustment

by   Yinyu Nie, et al.

Point completion refers to complete the missing geometries of objects from partial point clouds. Existing works usually estimate the missing shape by decoding a latent feature encoded from the input points. However, real-world objects are usually with diverse topologies and surface details, which a latent feature may fail to represent to recover a clean and complete surface. To this end, we propose a skeleton-bridged point completion network (SK-PCN) for shape completion. Given a partial scan, our method first predicts its 3D skeleton to obtain the global structure, and completes the surface by learning displacements from skeletal points. We decouple the shape completion into structure estimation and surface reconstruction, which eases the learning difficulty and benefits our method to obtain on-surface details. Besides, considering the missing features during encoding input points, SK-PCN adopts a local adjustment strategy that merges the input point cloud to our predictions for surface refinement. Comparing with previous methods, our skeleton-bridged manner better supports point normal estimation to obtain the full surface mesh beyond point clouds. The qualitative and quantitative experiments on both point cloud and mesh completion show that our approach outperforms the existing methods on various object categories.


page 7

page 9

page 15

page 16


LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints

Point cloud completion aims at completing geometric and topological shap...

ME-PCN: Point Completion Conditioned on Mask Emptiness

Point completion refers to completing the missing geometries of an objec...

SRPCN: Structure Retrieval based Point Completion Network

Given partial objects and some complete ones as references, point cloud ...

A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images

This paper focuses on the challenging task of learning 3D object surface...

Denoise and Contrast for Category Agnostic Shape Completion

In this paper, we present a deep learning model that exploits the power ...

Detail Preserved Point Cloud Completion via Separated Feature Aggregation

Point cloud shape completion is a challenging problem in 3D vision and r...

Bas-relief Generation from Point Clouds Based on Normal Space Compression with Real-time Adjustment on CPU

Bas-relief generation based on 3d models is a hot topic in computer grap...

Please sign up or login with your details

Forgot password? Click here to reset