☆ 4.5 Article

Point2MM: Learning medial mesh from point clouds

COMPUTERS & GRAPHICS-UK (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Software Engineering

Computing Medial Axis Transform with Feature Preservation via Restricted Power Diagram

Ningna Wang et al.

Summary: This paper proposes a novel framework using restricted power diagram (RPD) to compute the medial axis transform of 3D shapes, while preserving both external and internal medial features. The RPD provides connectivity and tangential surface regions of medial spheres, allowing for the detection and preservation of insufficient sphere sampling around medial features. Compared to existing methods, this framework is able to preserve a higher quality of the medial mesh.

ACM TRANSACTIONS ON GRAPHICS (2022)

添加到收藏夹

Article Computer Science, Software Engineering

SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform

Cheng Lin et al.

Summary: Segmenting arbitrary 3D objects into meaningful constituent parts is a crucial problem in computer graphics applications. Existing methods for 3D shape segmentation are limited by their reliance on low-level features and lack of global consideration, resulting in complex geometry processing and slow computation. This paper proposes SEG-MAT, a novel and efficient method based on the medial axis transform, which encodes rich geometric and structural information and effectively identifies various types of junctions between different parts of a 3D shape. Extensive evaluations demonstrate that our method outperforms state-of-the-art techniques in terms of segmentation quality and speed.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Deep Hybrid Self-Prior for Full 3D Mesh Generation

Xingkui Wei et al.

Summary: A deep learning pipeline is proposed to recover a full 3D model with a mesh and texture map from colored 3D point cloud using network self-prior. The method leverages both 2D and 3D self-prior in deep neural networks to improve geometry quality and produce high-resolution texture map. Experimental results show that the method outperforms state-of-the-art methods in terms of both geometry and texture quality without requiring additional training data.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Point2Skeleton: Learning Skeletal Representations from Point Clouds

Cheng Lin et al.

Summary: Point2Skeleton is an unsupervised method for learning skeletal representations from point clouds, which can handle complex structures and has superior performance and robustness. The method predicts skeletal points using a geometric transformation and analyzes their connectivity to form skeletal mesh structures, benefiting several unsupervised tasks for point clouds such as surface reconstruction and segmentation.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Medial Elastics: Efficient and Collision-Ready Deformation via Medial Axis Transform

Lei Lan et al.

ACM TRANSACTIONS ON GRAPHICS (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Point2Mesh: A Self-Prior for Deformable Meshes

Rana Hanocka et al.

ACM TRANSACTIONS ON GRAPHICS (2020)

添加到收藏夹

Article Computer Science, Software Engineering

P2MAT-NET: Learning medial axis transform from sparse point clouds

Baorong Yang et al.

COMPUTER AIDED GEOMETRIC DESIGN (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Mass-Driven Topology-Aware Curve Skeleton Extraction from Incomplete Point Clouds

Hongxing Qin et al.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Q-MAT plus : An error-controllable and feature-sensitive simplification algorithm for medial axis transform

Yiling Pan et al.

COMPUTER AIDED GEOMETRIC DESIGN (2019)

添加到收藏夹

Article Computer Science, Software Engineering

MeshCNN: A Network with an Edge

Rana Hanocka et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

添加到收藏夹

Article Computer Science, Software Engineering

DMAT: Deformable Medial Axis Transform for Animated Mesh Approximation

Baorong Yang et al.

COMPUTER GRAPHICS FORUM (2018)

添加到收藏夹

Article Computer Science, Information Systems

3D tree modeling from incomplete point clouds via optimization and L1-MST

Jie Mei et al.

INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE (2017)

添加到收藏夹

Article Computer Science, Software Engineering

Medial Meshes - A Compact and Accurate Representation of Medial Axis Transform

Feng Sun et al.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2016)

添加到收藏夹

Article Engineering, Electrical & Electronic

DeepPano: Deep Panoramic Representation for 3-D Shape Recognition

Baoguang Shi et al.

IEEE SIGNAL PROCESSING LETTERS (2015)

添加到收藏夹

Article Computer Science, Software Engineering

L1-Medial Skeleton of Point Cloud

Hui Huang et al.

ACM TRANSACTIONS ON GRAPHICS (2013)

添加到收藏夹

Article Computer Science, Software Engineering

Screened Poisson Surface Reconstruction

Michael Kazhdan et al.

ACM TRANSACTIONS ON GRAPHICS (2013)

添加到收藏夹

Article Computer Science, Software Engineering

Curve Skeleton Extraction from Incomplete Point Cloud

Andrea Tagliasacchi et al.

ACM TRANSACTIONS ON GRAPHICS (2009)

添加到收藏夹

Article Computer Science, Software Engineering

The λ-medial axis

F Chazal et al.

GRAPHICAL MODELS (2005)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.