Voxel-based Network for Shape Completion by Leveraging Edge Generation

08/23/2021
by   Xiaogang Wang, et al.
0

Deep learning technique has yielded significant improvements in point cloud completion with the aim of completing missing object shapes from partial inputs. However, most existing methods fail to recover realistic structures due to over-smoothing of fine-grained details. In this paper, we develop a voxel-based network for point cloud completion by leveraging edge generation (VE-PCN). We first embed point clouds into regular voxel grids, and then generate complete objects with the help of the hallucinated shape edges. This decoupled architecture together with a multi-scale grid feature learning is able to generate more realistic on-surface details. We evaluate our model on the publicly available completion datasets and show that it outperforms existing state-of-the-art approaches quantitatively and qualitatively. Our source code is available at https://github.com/xiaogangw/VE-PCN.

READ FULL TEXT
research
04/07/2020

Cascaded Refinement Network for Point Cloud Completion

Point clouds are often sparse and incomplete. Existing shape completion ...
research
02/02/2020

Adversarial Generation of Continuous Implicit Shape Representations

This work presents a generative adversarial architecture for generating ...
research
07/21/2022

SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer

Point cloud completion has become increasingly popular among generation ...
research
07/28/2023

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

Conditional 3D generation is undergoing a significant advancement, enabl...
research
10/17/2020

A Self-supervised Cascaded Refinement Network for Point Cloud Completion

Point clouds are often sparse and incomplete, which imposes difficulties...
research
08/18/2021

ME-PCN: Point Completion Conditioned on Mask Emptiness

Point completion refers to completing the missing geometries of an objec...
research
03/24/2022

WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation

We propose WarpingGAN, an effective and efficient 3D point cloud generat...

Please sign up or login with your details

Forgot password? Click here to reset