Search Results for author: Mingye Xu

Found 6 papers, 5 papers with code

CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning

no code implementations20 Jan 2022 Mingye Xu, Yali Wang, Zhipeng Zhou, Hongbin Xu, Yu Qiao

To fill this gap, we propose a generic Contour-Perturbed Reconstruction Network (CP-Net), which can effectively guide self-supervised reconstruction to learn semantic content in the point cloud, and thus promote discriminative power of point cloud representation.

Point cloud reconstruction Self-Supervised Learning

Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud

1 code implementation18 Mar 2021 Mingye Xu, Zhipeng Zhou, Junhao Zhang, Yu Qiao

This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds.

3D Semantic Segmentation

Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud

1 code implementation20 Dec 2020 Mutian Xu, Junhao Zhang, Zhipeng Zhou, Mingye Xu, Xiaojuan Qi, Yu Qiao

GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components.

3D Object Classification 3D Part Segmentation

Geometry Sharing Network for 3D Point Cloud Classification and Segmentation

1 code implementation23 Dec 2019 Mingye Xu, Zhipeng Zhou, Yu Qiao

Specially, GS-Net consists of Geometry Similarity Connection (GSC) modules which exploit Eigen-Graph to group distant points with similar and relevant geometric information, and aggregate features from nearest neighbors in both Euclidean space and Eigenvalue space.

3D Point Cloud Classification Classification +3

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

1 code implementation ECCV 2018 Yifan Xu, Tianqi Fan, Mingye Xu, Long Zeng, Yu Qiao

Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds.

3D Part Segmentation 3D Point Cloud Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.