Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds

2021-01-07 · Jingyu Gong, Jiachen Xu, Xin Tan, Jie zhou, Yanyun Qu, Yuan Xie, Lizhuang Ma

Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects. In this paper, firstly, we propose a Boundary Prediction Module (BPM) to predict boundary points. Based on the predicted boundary, a boundary-aware Geometric Encoding Module (GEM) is designed to encode geometric information and aggregate features with discrimination in a neighborhood, so that the local features belonging to different categories will not be polluted by each other. To provide extra geometric information for boundary-aware GEM, we also propose a light-weight Geometric Convolution Operation (GCO), making the extracted features more distinguishing. Built upon the boundary-aware GEM, we build our network and test it on benchmarks like ScanNet v2, S3DIS. Results show our methods can significantly improve the baseline and achieve state-of-the-art performance. Code is available at https://github.com/JchenXu/BoundaryAwareGEM.

📄 PDF Abstract BibTeX arXiv:2101.02381

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentation Point Cloud Segmentation Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Graph-BAS3Net: Boundary-Aware Semi-Supervised Segmentation Network With Bilateral Graph Convolution

2021-01-01 · ICCV 2021 10 · Huimin Huang, Lanfen Lin, Yue Zhang, Yingying Xu 외

Semi-supervised learning (SSL) algorithms have attracted much attentions in medical image segmentation by leveraging unlabeled data, which challenge in acquiring massive pixel-wise annotated samples. However, most of…

Boundary Detection Image Segmentation Medical Image Segmentation Multi-Task Learning+4

Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Clouds

2022-12-23 · Shenglan Du, Nail Ibrahimli, Jantien Stoter, Julian Kooij 외

Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local information at low-level layers, posing sign…

Multi-Task Learning Object Scene Segmentation Segmentation+1

SOFTooth: Semantics-Enhanced Order-Aware Fusion for Tooth Instance Segmentation

2025-12-29 · Xiaolan Li, Wanquan Liu, Pengcheng Li, Pengyu Jie 외 arxiv

Three-dimensional (3D) tooth instance segmentation remains challenging due to crowded arches, ambiguous tooth-gingiva boundaries, missing teeth, and rare yet clinically important third molars. Native 3D methods relying o…

Instance Segmentation

GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modeling

2022-07-14 · Chen Chen, Yisen Wang, Honghua Chen, Xuefeng Yan 외

Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding.Despite of significant advances in recent years, most of existing methods still suffer from ei…

Decoder Object Segmentation Semantic Segmentation

Gland Segmentation Via Dual Encoders and Boundary-Enhanced Attention

2024-01-29 · Huadeng Wang, Jiejiang Yu, Bingbing Li, Xipeng Pan 외

Accurate and automated gland segmentation on pathological images can assist pathologists in diagnosing the malignancy of colorectal adenocarcinoma. However, due to various gland shapes, severe deformation of malignant gl…

Decoder Segmentation