AI Paper Atlas

Research map / 3D vision / Depth and stereo

End-to-End Learning of Keypoint Detector and Descriptor for Pose Invariant 3D Matching

Georgios Georgakis, Srikrishna Karanam, Ziyan Wu, Jan Ernst, Jana Košecká

CVPR 2018 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 67 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
Add the score loss to train the detector alongside contrastive descriptor learning (ablation)Ours · Engine noisymatching accuracy (%): 11.1 -> 23.8Improved
Add the score loss to train the detector alongside contrastive descriptor learning (ablation)Ours · Stanford 3D models noisy, averagematching accuracy (%): 16.5 -> 32.6Improved
Select keypoints by learned scores rather than randomly (ablation)Ours · Engine noisymatching accuracy (%): 7.3 -> 23.8Improved
Train on noisy rather than noise-free views (ablation)Ours · Engine noisymatching accuracy (%): 17.8 -> 23.8Improved
Jointly learn keypoint detection and descriptors instead of using the strongest listed baselineOurs · Stanford 3D models noisy, averagematching accuracy (%): 18.8 -> 32.6Improved
Jointly learn keypoint detection and descriptors instead of using the strongest listed baselineOurs · MSR-7matching accuracy (%): 38.2 -> 41.2Improved
Use the learned method instead of Harris3D+FPFHOurs · Engine noise-freematching accuracy (%): 79.1 -> 67.4Hurt

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