computer-vision

Point Cloud Completion

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in point-cloud-completion

Trend

Dataset

Best Model

Actions

ShapeNet

Completion3D

ShapeNet-ViPC

Libraries

i

Use these libraries to find point-cloud-completion models and implementations

Datasets

ShapeNet

Completion3D

MVP

ShapeNet-ViPC

Subtasks

Point Cloud Semantic Completion

Most implemented papers

Pointer Networks

O. Vinyals, N. Jaitly, Meire Fortunato•Mon Jun 08 2015

A new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence using a recently proposed mechanism of neural attention, called Ptr-Nets, which improves over sequence-to-sequence with input attention, but also allows it to generalize to variable size output dictionaries.

3331

Content

0

Paper Graph

SPCNet: Stepwise Point Cloud Completion Network

Fei-Jiang Hu, Honghua Chen, Xuequan Lu, Zhenliang Zhu, Jun Wang, Weiming Wang, F. Wang, Mingqiang Wei•Sun Sep 04 2022

This work proposes a novel stepwise point cloud completion network (SPCNet) for various 3D models with large missings and newly design a cycle loss to enhance the generalization and robustness of SPCNet.

5 0

Paper Graph

A Papier-Mache Approach to Learning 3D Surface Generation

Bryan C. Russell, Matthew Fisher, Mathieu Aubry, Thibault Groueix, Vladimir G. Kim•Wed Feb 14 2018

This work introduces a method for learning to generate the surface of 3D shapes as a collection of parametric surface elements and, in contrast to methods generating voxel grids or point clouds, naturally infers a surface representation of the shape.

1283 0

Paper Graph

PF-Net: Point Fractal Network for 3D Point Cloud Completion

Feng Ni, Zitian Huang, Yikuan Yu, Jiawen Xu, Xinyi Le•Sat Feb 29 2020

A Point Fractal Network (PF-Net), a novel learning-based approach for precise and high-fidelity point cloud completion that preserves the spatial arrangements of the incomplete point cloud and can figure out the detailed geometrical structure of the missing region(s) in the prediction.

424 0

Paper Graph

PCN: Point Completion Network

David Held, M. Hebert, Tejas Khot, C. Mertz, Wentao Yuan•Wed Aug 01 2018

The experiments show that PCN produces dense, complete point clouds with realistic structures in the missing regions on inputs with various levels of incompleteness and noise, including cars from LiDAR scans in the KITTI dataset.

985 0

Paper Graph

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer

Peng Xiang, Xin Wen, Yu-Shen Liu, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Zhizhong Han•Mon Aug 09 2021

SnowflakeNet with Snowflake Point Deconvolution (SPD) is proposed with skip-transformer in SPD to learn point splitting patterns which can fit local regions the best and outperform the state-of-the-art point cloud completion methods under widely used benchmarks.

296 0

Paper Graph

Unpaired Point Cloud Completion on Real Scans using Adversarial Training

N. Mitra, Baoquan Chen, Xuelin Chen•Thu Mar 28 2019

This work develops a first approach that works directly on input point clouds, does not require paired training data, and hence can directly be applied to real scans for scan completion.

141 0

Paper Graph

KT-Net: Knowledge Transfer for Unpaired 3D Shape Completion

Bisheng Yang, Wenxiao Zhang, Xin Wen, Yu-Shen Liu, Zhenhua Cao•Mon Nov 22 2021

The novel KTNet elaborates a teacher-assistant-student network to establish multiple knowledge transfer processes to establish the geometric correspondence between complete and incomplete shapes in a perspective of knowledge transfer, which enables more detailed geometric inference for generating high-quality complete shapes.

15 0

Paper Graph

Morphing and Sampling Network for Dense Point Cloud Completion

Shimin Hu, Jing Shao, Minghua Liu, Lu Sheng, Sheng Yang•Fri Nov 29 2019

This work proposes a novel approach to complete the partial point cloud in two stages, which outperforms the existing methods in both the Earth Mover's Distance (EMD) and the Chamfer Distance (CD).

351 0

Paper Graph

Refinement of Predicted Missing Parts Enhance Point Cloud Completion

I. Sipiran, Alexis Mendoza, Alex Apaza, Cristian Lopez•Wed Oct 07 2020

An end-to-end neural network architecture that focuses on computing the missing geometry and merging the known input and the predicted point cloud that outperforms the state-of-the-art methods in point cloud completion is proposed.

7 0

Paper Graph

Adding a benchmark result helps the community track progress.