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/3D Point Capsule Networks

3D Point Capsule Networks

Yongheng Zhao, Tolga Birdal, Haowen Deng, Federico Tombari

2018-12-27CVPR 2019 63D Point Cloud Matching3D Shape Representation3D Object Reconstruction3D Geometry Perception3D Object ClassificationGeneral Classification3D Part Segmentation3D Feature Matching3D Shape Generation
PaperPDFCodeCode

Abstract

In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data. 3D capsule networks arise as a direct consequence of our novel unified 3D auto-encoder formulation. Their dynamic routing scheme and the peculiar 2D latent space deployed by our approach bring in improvements for several common point cloud-related tasks, such as object classification, object reconstruction and part segmentation as substantiated by our extensive evaluations. Moreover, it enables new applications such as part interpolation and replacement.

Results

TaskDatasetMetricValueModel
3DModelNet40Classification Accuracy89.33D-PointCapsNet
Shape Representation Of 3D Point CloudsModelNet40Classification Accuracy89.33D-PointCapsNet
3D Object ClassificationModelNet40Classification Accuracy89.33D-PointCapsNet
3D Point Cloud ClassificationModelNet40Classification Accuracy89.33D-PointCapsNet
3D ClassificationModelNet40Classification Accuracy89.33D-PointCapsNet
3D Point Cloud ReconstructionModelNet40Classification Accuracy89.33D-PointCapsNet

Related Papers

3D Shape Generation: A Survey2025-06-27HuSc3D: Human Sculpture dataset for 3D object reconstruction2025-06-09Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations2025-06-05SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping2025-05-30LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework2025-05-30Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention2025-05-23TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians2025-04-263D Object Reconstruction with mmWave Radars2025-04-15