TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/A-CNN: Annularly Convolutional Neural Networks on Point Cl...

A-CNN: Annularly Convolutional Neural Networks on Point Clouds

Artem Komarichev, Zichun Zhong, Jing Hua

2019-04-16CVPR 2019 6SegmentationSemantic Segmentation3D Point Cloud Classification
PaperPDFCode(official)

Abstract

Analyzing the geometric and semantic properties of 3D point clouds through the deep networks is still challenging due to the irregularity and sparsity of samplings of their geometric structures. This paper presents a new method to define and compute convolution directly on 3D point clouds by the proposed annular convolution. This new convolution operator can better capture the local neighborhood geometry of each point by specifying the (regular and dilated) ring-shaped structures and directions in the computation. It can adapt to the geometric variability and scalability at the signal processing level. We apply it to the developed hierarchical neural networks for object classification, part segmentation, and semantic segmentation in large-scale scenes. The extensive experiments and comparisons demonstrate that our approach outperforms the state-of-the-art methods on a variety of standard benchmark datasets (e.g., ModelNet10, ModelNet40, ShapeNet-part, S3DIS, and ScanNet).

Results

TaskDatasetMetricValueModel
Semantic SegmentationS3DISoAcc88.1PointCNN
Semantic SegmentationS3DISMean IoU62.9A-CNN
Semantic SegmentationS3DISoAcc87.3A-CNN
Semantic SegmentationS3DISoAcc85.5SPGraph
Semantic SegmentationS3DISMean IoU56.33P-RNN
Semantic SegmentationS3DISoAcc86.93P-RNN
Semantic SegmentationS3DISoAcc78.5PointNet
Shape Representation Of 3D Point CloudsModelNet40Overall Accuracy92.6A-CNN
3D Point Cloud ClassificationModelNet40Overall Accuracy92.6A-CNN
10-shot image generationS3DISoAcc88.1PointCNN
10-shot image generationS3DISMean IoU62.9A-CNN
10-shot image generationS3DISoAcc87.3A-CNN
10-shot image generationS3DISoAcc85.5SPGraph
10-shot image generationS3DISMean IoU56.33P-RNN
10-shot image generationS3DISoAcc86.93P-RNN
10-shot image generationS3DISoAcc78.5PointNet
3D Point Cloud ReconstructionModelNet40Overall Accuracy92.6A-CNN

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21Deep Learning-Based Fetal Lung Segmentation from Diffusion-weighted MRI Images and Lung Maturity Evaluation for Fetal Growth Restriction2025-07-17DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure Segmentation2025-07-17Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion2025-07-17SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique2025-07-17