AI Paper Atlas

Research map / Point clouds / Registration and matching

3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

Zi Jian Yew, Gim Hee Lee

ECCV 2018 · Point clouds › Registration and matching · approach: Learned feature-based registration · 402 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use the learned attention keypoint detector instead of ISS (ablation)3DFeat-Net descriptor · Oxford RobotCar registrationsuccess rate: 97.66% -> 98.10%Improved
use the learned detector instead of random sampling (ablation)3DFeat-Net descriptor · Oxford RobotCar registrationsuccess rate: 90.28% -> 98.10%Improved
use the learned detector instead of Random Sphere Cover Set (ablation)3DFeat-Net descriptor · Oxford RobotCar registrationsuccess rate: 92.64% -> 98.10%Improved
use the learned detector instead of ISS (ablation)3DFeat-Net descriptor · Oxford RobotCar registrationavg RANSAC iterations: 7127 -> 2940Improved
use keypoint detector (ISS) instead of random sampling for 3DMatch (ablation)3DMatch · Oxford RobotCar registrationsuccess rate: 54.64% -> 69.06%Improved
plug the learned descriptor into handcrafted detector rather than FPFH descriptor (ablation)ISS keypoints · Oxford RobotCar registrationsuccess rate: 92.32% -> 97.66%Improved
train PointNet++ without descriptor alignment in the weak setting (ablation)PointNet++ descriptor · Oxford RobotCar descriptor matchingerror at 95% recall: 36.84 -> 50.57Hurt
increase descriptor dimension above 32 (ablation)3DFeat-Net descriptor · Oxford RobotCar descriptor matchingerror at 95% recallNo clear effect
apply learned model to KITTI without fine-tuning versus ISS+FPFH3DFeat-Net · KITTI odometry registration (no fine-tuning)success rate: 58.95% -> 95.97%Improved
compare with LORAX on ETH using single best match and no refinement3DFeat-Net · ETH dataset registration (best point clouds)success rate: 83% -> 100%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy