3D Point Cloud Matching

8 papers with code • 0 benchmarks • 3 datasets

Image: Gojic et al

Most implemented papers

The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

zgojcic/3DSmoothNet CVPR 2019

Our approach is sensor- and sceneagnostic because of SDV, LRF and learning highly descriptive features with fully convolutional layers.

3D Point Capsule Networks

yongheng1991/3D-point-capsule-networks CVPR 2019

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.

Robust Point Set Registration Using Gaussian Mixture Models

bing-jian/gmmreg IEEE Transactions on Pattern Analysis and Machine Intelligence 2010

Then, the problem of point set registration is reformulated as the problem of aligning two Gaussian mixtures such that a statistical discrepancy measure between the two corresponding mixtures is minimized.

3D-CODED : 3D Correspondences by Deep Deformation

ThibaultGROUEIX/3D-CODED 13 Jun 2018

By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template.

Fully Convolutional Geometric Features

chrischoy/FCGF International Conference on Computer vision 2019

Extracting geometric features from 3D scans or point clouds is the first step in applications such as registration, reconstruction, and tracking.

LCD: Learned Cross-Domain Descriptors for 2D-3D Matching

hkust-vgd/lcd 21 Nov 2019

In this work, we present a novel method to learn a local cross-domain descriptor for 2D image and 3D point cloud matching.

Human Correspondence Consensus for 3D Object Semantic Understanding

yokinglou/CorresPondenceNet ECCV 2020

Semantic understanding of 3D objects is crucial in many applications such as object manipulation.

Lepard: Learning partial point cloud matching in rigid and deformable scenes

rabbityl/lepard CVPR 2022

We present Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes.