3D Feature Matching

8 papers with code • 1 benchmarks • 4 datasets

Image: Choy et al

Most implemented papers

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.

PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features

qq456cvb/SPRIN 24 Feb 2021

Spherical Voxel Convolution and Point Re-sampling are proposed to extract rotation invariant features for each point.

Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution

qq456cvb/PRIN 23 Nov 2018

Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown.

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.

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.

Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution

HCIILAB/EPHOIE 24 Jan 2021

Visual information extraction (VIE) has attracted considerable attention recently owing to its various advanced applications such as document understanding, automatic marking and intelligent education.

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.

Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition

axeber01/point-tnt 8 Apr 2022

While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial.