AI Paper Atlas

Research map / Point clouds / Registration and matching

RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor

Fan Lu, Guang Chen, Yinlong Liu, Zhongnan Qu, Alois Knoll

NeurIPS 2020 · Point clouds › Registration and matching · approach: Learned feature-based registration · 33 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 RSKDD-Net (random sampling + learned keypoints/descriptors) instead of USIPkeypoint detector and descriptor · KITTI registrationinlier ratio: 0.243 -> 0.586Improved
use RSKDD-Net instead of USIPkeypoint detector and descriptor · KITTI registrationRANSAC iterations: 468 -> 32Improved
use RSKDD-Net instead of USIPkeypoint detector and descriptor · KITTI registrationRRE (deg): 0.35 -> 0.50Hurt
use RSKDD-Net instead of USIPkeypoint detector and descriptor · KITTI registrationRTE (m): 0.10 -> 0.09Improved
use random sampling instead of FPS/per-point saliencykeypoint detection · KITTI, 16384 points, 512 keypointstime (ms): 378.5 -> 10.1Improved
add random dilation cluster (versus plain kNN cluster) (ablation)RSKDD-Net · KITTIrepeatability and precisionImproved
use random dilation instead of dilated point convolution (DPC) (ablation)RSKDD-Net · KITTIprecisionNo clear effect
add attentive feature map to descriptor network (ablation)RSKDD-Net · KITTIprecision: +0.1 precisionImproved
replace triplet loss with proposed soft-assignment matching loss (ablation)RSKDD-Net · KITTIprecision: about 2x precisionImproved
increase matching-loss temperature t to 0.5 (ablation)RSKDD-Net · KITTIprecisionHurt
add keypoint saliency weight to matching loss (ablation)RSKDD-Net · KITTIprecisionImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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