Papers with Code 아카이브
Point Cloud Registration
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration
LPRnet: A self-supervised registration network for LiDAR and photogrammetric point clouds
MRG: A Multi-Robot Manufacturing Digital Scene Generation Method Using Multi-Instance Point Cloud Registration
Towards Explaining Uncertainty Estimates in Point Cloud Registration
Resolving the Ambiguity of Complete-to-Partial Point Cloud Registration for Image-Guided Liver Surgery with Patches-to-Partial Matching
Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework
PointVoxelFormer -- Reviving point cloud networks for 3D medical imaging
3D Registration in 30 Years: A Survey
TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes
AutoURDF: Unsupervised Robot Modeling from Point Cloud Frames Using Cluster Registration
GS-Matching: Reconsidering Feature Matching task in Point Cloud Registration
QuadricsReg: Large-Scale Point Cloud Registration using Quadric Primitives
FlashSLAM: Accelerated RGB-D SLAM for Real-Time 3D Scene Reconstruction with Gaussian Splatting
XR-MBT: Multi-modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration
EADReg: Probabilistic Correspondence Generation with Efficient Autoregressive Diffusion Model for Outdoor Point Cloud Registration
Automatic marker-free registration based on similar tetrahedras for single-tree point clouds
3D Reconstruction by Looking: Instantaneous Blind Spot Detector for Indoor SLAM through Mixed Reality
Deep Loss Convexification for Learning Iterative Models
3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registration
Memory-Efficient Point Cloud Registration via Overlapping Region Sampling
Micro-Structures Graph-Based Point Cloud Registration for Balancing Efficiency and Accuracy
RANSAC Back to SOTA: A Two-stage Consensus Filtering for Real-time 3D Registration
A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration
Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration
LoGDesc: Local geometric features aggregation for robust point cloud registration
TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registration
GERA: Geometric Embedding for Efficient Point Registration Analysis
MATCH POLICY: A Simple Pipeline from Point Cloud Registration to Manipulation Policies
KISS-Matcher: Fast and Robust Point Cloud Registration Revisited
SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registration
FracGM: A Fast Fractional Programming Technique for Geman-McClure Robust Estimator
Registration between Point Cloud Streams and Sequential Bounding Boxes via Gradient Descent
Unsupervised Point Cloud Registration with Self-Distillation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.