TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Deep Global Registration

Deep Global Registration

Christopher Choy, Wei Dong, Vladlen Koltun

2020-04-24CVPR 2020 6Point Cloud RegistrationPose Estimation
PaperPDFCode(official)Code

Abstract

We present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans. Deep global registration is based on three modules: a 6-dimensional convolutional network for correspondence confidence prediction, a differentiable Weighted Procrustes algorithm for closed-form pose estimation, and a robust gradient-based SE(3) optimizer for pose refinement. Experiments demonstrate that our approach outperforms state-of-the-art methods, both learning-based and classical, on real-world data.

Results

TaskDatasetMetricValueModel
Point Cloud Registration3DLoMatch (10-30% overlap)Recall ( correspondence RMSE below 0.2)48.7DGR (reported in REGTR)
Point Cloud Registration3DMatch (at least 30% overlapped - FCGF setting)RE (all)9.5DGR (RE (all), TE(all) are reported in PCAM)
Point Cloud Registration3DMatch (at least 30% overlapped - FCGF setting)Recall (0.3m, 15 degrees)91.3DGR (RE (all), TE(all) are reported in PCAM)
Point Cloud Registration3DMatch (at least 30% overlapped - FCGF setting)TE (all)0.25DGR (RE (all), TE(all) are reported in PCAM)
Point Cloud RegistrationKITTI (FCGF setting)RE (all)1.43DGR + ICP (RE (all), TE(all) are reported in PCAM)
Point Cloud RegistrationKITTI (FCGF setting)Recall (0.6m, 5 degrees)98.2DGR + ICP (RE (all), TE(all) are reported in PCAM)
Point Cloud RegistrationKITTI (FCGF setting)TE (all)0.16DGR + ICP (RE (all), TE(all) are reported in PCAM)
Point Cloud RegistrationKITTI (FCGF setting)RE (all)1.62DGR (RE (all), TE(all) are reported in PCAM)
Point Cloud RegistrationKITTI (FCGF setting)Recall (0.6m, 5 degrees)96.9DGR (RE (all), TE(all) are reported in PCAM)
Point Cloud RegistrationKITTI (FCGF setting)TE (all)0.34DGR (RE (all), TE(all) are reported in PCAM)
Point Cloud Registration3DMatch (at least 30% overlapped - sample 5k interest points)Recall ( correspondence RMSE below 0.2)85.3DGR (reported in REGTR)
3D Point Cloud Interpolation3DLoMatch (10-30% overlap)Recall ( correspondence RMSE below 0.2)48.7DGR (reported in REGTR)
3D Point Cloud Interpolation3DMatch (at least 30% overlapped - FCGF setting)RE (all)9.5DGR (RE (all), TE(all) are reported in PCAM)
3D Point Cloud Interpolation3DMatch (at least 30% overlapped - FCGF setting)Recall (0.3m, 15 degrees)91.3DGR (RE (all), TE(all) are reported in PCAM)
3D Point Cloud Interpolation3DMatch (at least 30% overlapped - FCGF setting)TE (all)0.25DGR (RE (all), TE(all) are reported in PCAM)
3D Point Cloud InterpolationKITTI (FCGF setting)RE (all)1.43DGR + ICP (RE (all), TE(all) are reported in PCAM)
3D Point Cloud InterpolationKITTI (FCGF setting)Recall (0.6m, 5 degrees)98.2DGR + ICP (RE (all), TE(all) are reported in PCAM)
3D Point Cloud InterpolationKITTI (FCGF setting)TE (all)0.16DGR + ICP (RE (all), TE(all) are reported in PCAM)
3D Point Cloud InterpolationKITTI (FCGF setting)RE (all)1.62DGR (RE (all), TE(all) are reported in PCAM)
3D Point Cloud InterpolationKITTI (FCGF setting)Recall (0.6m, 5 degrees)96.9DGR (RE (all), TE(all) are reported in PCAM)
3D Point Cloud InterpolationKITTI (FCGF setting)TE (all)0.34DGR (RE (all), TE(all) are reported in PCAM)
3D Point Cloud Interpolation3DMatch (at least 30% overlapped - sample 5k interest points)Recall ( correspondence RMSE below 0.2)85.3DGR (reported in REGTR)

Related Papers

$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning2025-07-17Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark2025-07-17DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model2025-07-17From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation2025-07-17AthleticsPose: Authentic Sports Motion Dataset on Athletic Field and Evaluation of Monocular 3D Pose Estimation Ability2025-07-17A Multi-Level Similarity Approach for Single-View Object Grasping: Matching, Planning, and Fine-Tuning2025-07-16SpatialTrackerV2: 3D Point Tracking Made Easy2025-07-16SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting Representation2025-07-16