Papers with Code 아카이브

Point Cloud Registration

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 24
보존된 평가 기록: 190

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.

Source: Iterative Global Similarity Points : A robust coarse-to-fine integration solution for pairwise 3D point cloud registration

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/mahdi-slh/Graphite

공식 코드

Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration

https://github.com/marineroboticsgroup/dcsam

공식 코드

Discrete-Continuous Smoothing and Mapping

https://github.com/mbanani/unsupervisedRR

공식 코드

UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering

https://github.com/mcdermatt/icet

공식 코드

ICET Online Accuracy Characterization for Geometry-Based Laser Scan Matching

https://github.com/megvii-research/FINet

공식 코드

FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration

https://github.com/megvii-research/omnet

공식 코드

OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration

https://github.com/mhorn11/deepclr

공식 코드

DeepCLR: Correspondence-Less Architecture for Deep End-to-End Point Cloud Registration

https://github.com/minghanz/equivreg

공식 코드

Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations

https://github.com/minnjung/ep2p-loc

공식 코드

EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization

https://github.com/mit-acl/clipper

공식 코드

CLIPPER: A Graph-Theoretic Framework for Robust Data Association

https://github.com/mit-spark/buffer-x

공식 코드

BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes

https://github.com/mit-spark/kiss-matcher

공식 코드

KISS-Matcher: Fast and Robust Point Cloud Registration Revisited

https://github.com/muhammadsaeedbatikh/knn-res_demo

공식 코드

kNN-Res: Residual Neural Network with kNN-Graph coherence for point cloud registration

https://github.com/multimodallearning/deep-geo-reg

공식 코드

Deep learning based geometric registration for medical images: How accurate can we get without visual features?

https://github.com/multimodallearning/denoised_mt_pcd_reg

공식 코드

A denoised Mean Teacher for domain adaptive point cloud registration

https://github.com/muyao99/tfct-i2p

공식 코드

TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registration

https://github.com/neu-vi/superpoints_registration

공식 코드

A Strong Baseline for Point Cloud Registration via Direct Superpoints Matching

https://github.com/numerical-geometric-algebra/registrationga

공식 코드

Correspondence Free Multivector Cloud Registration using Conformal Geometric Algebra

https://github.com/omron-sinicx/weavenet

공식 코드

3D Point Cloud Registration with Learning-based Matching Algorithm

https://github.com/paul007pl/MVP_Benchmark

공식 코드

Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results

https://github.com/paul007pl/gmcnet

공식 코드

Robust Partial-to-Partial Point Cloud Registration in a Full Range

https://github.com/peakpang/ugp

공식 코드

Unlocking Generalization Power in LiDAR Point Cloud Registration

https://github.com/peterstratton/volume-droid

공식 코드

Volume-DROID: A Real-Time Implementation of Volumetric Mapping with DROID-SLAM

https://github.com/phdymz/pointclm

공식 코드

PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration

https://github.com/phdymz/pointmbf

공식 코드

PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration

https://github.com/pranavkdm/R-PointHop

공식 코드

R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method

https://github.com/qiaozhijian/VCR-Net

공식 코드

End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences

https://github.com/qinzheng93/geotransformer

공식 코드

Geometric Transformer for Fast and Robust Point Cloud Registration

https://github.com/qinzheng93/graphscnet

공식 코드

Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration

https://github.com/rabbityl/deformationpyramid

공식 코드

Non-rigid Point Cloud Registration with Neural Deformation Pyramid

https://github.com/rabbityl/lepard

공식 코드

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

https://github.com/renlanghuang/cast

공식 코드

A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration

https://github.com/rlit/LatentRANSAC

공식 코드

https://github.com/robot-learning-freiburg/LCDNet

공식 코드

LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM

https://github.com/rsy6318/CorrI2P

공식 코드

CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence

https://github.com/sayands/sgaligner

공식 코드

SGAligner : 3D Scene Alignment with Scene Graphs

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.