Point Cloud Registration
185 papers with code • 22 benchmarks • 11 datasets
Point Cloud Registration is a fundamental problem in 3D computer vision and photogrammetry. Given several sets of points in different coordinate systems, the aim of registration is to find the transformation that best aligns all of them into a common coordinate system. Point Cloud Registration plays a significant role in many vision applications such as 3D model reconstruction, cultural heritage management, landslide monitoring and solar energy analysis.
Benchmarks
These leaderboards are used to track progress in Point Cloud Registration
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Point Cloud Registration models and implementationsDatasets
KITTI
3DMatch
DeformingThings4D
3RScan
UrbanLoco
4DMatch
3DCSR dataset
FPv1
FAUST-partial
VBR
Most implemented papers
DVI: Depth Guided Video Inpainting for Autonomous Driving
To get clear street-view and photo-realistic simulation in autonomous driving, we present an automatic video inpainting algorithm that can remove traffic agents from videos and synthesize missing regions with the guidance of depth/point cloud.
DeepGMR: Learning Latent Gaussian Mixture Models for Registration
wentaoyuan/deepgmr
•
•
ECCV 2020
Point cloud registration is a fundamental problem in 3D computer vision, graphics and robotics.
Distinctive 3D local deep descriptors
fabiopoiesi/dip
•
•
We present a simple but yet effective method for learning distinctive 3D local deep descriptors (DIPs) that can be used to register point clouds without requiring an initial alignment.
MaskNet: A Fully-Convolutional Network to Estimate Inlier Points
We demonstrate these improvements on synthetic and real-world datasets.
CLIPPER: A Graph-Theoretic Framework for Robust Data Association
We formulate the problem in a graph-theoretic framework using the notion of geometric consistency.
Self-supervised Geometric Perception
theNded/SGP
•
•
CVPR 2021
We present self-supervised geometric perception (SGP), the first general framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels (e. g., camera poses, rigid transformations).
Robust Point Cloud Registration Framework Based on Deep Graph Matching
fukexue/RGM
•
•
CVPR 2021
In this paper, we propose a novel deep graph matchingbased framework for point cloud registration.
ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning
Point cloud registration is a common step in many 3D computer vision tasks such as object pose estimation, where a 3D model is aligned to an observation.
Accurate Point Cloud Registration with Robust Optimal Transport
uncbiag/shapmagn
•
•
NeurIPS 2021
Finally, we showcase the performance of transport-enhanced registration models on a wide range of challenging tasks: rigid registration for partial shapes; scene flow estimation on the Kitti dataset; and nonparametric registration of lung vascular trees between inspiration and expiration.
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
