AI Paper Atlas

Research map / Point clouds / Registration and matching

Density-invariant Features for Distant Point Cloud Registration

Quan Liu, Hongzi Zhu, Yunsong Zhou, Hongyang Li, Shan Chang, Minyi Guo

ICCV 2023 · Point clouds › Registration and matching · approach: Learned feature-based registration · 20 citations (OpenAlex)

Read the paper

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
replace pair-wise contrastive learning with group-wise contrastive learning (GCL)distant point cloud registration, KITTI · KITTI [40,50]registration recall (%): 26.7 -> 67.6Improved
GCL on nuScenes mean over distance binsdistant point cloud registration, nuScenes · nuScenes mRRmRR (%): 39.5 -> 71.5Improved
GCL on easy close-range pairsKITTI [5,10] and [10,20] · KITTI easy binsregistration recall (%): Predator 96.8 vs GCL+Conv 96.1 on [10,20]No clear effect
increase number of point clouds per positive group phi from 2 to 6 (ablation)GCL+Conv · LoKITTIregistration recall (%): 46.3 -> 72.3Improved
increase phi beyond 6 (8, 10) (ablation)GCL+Conv · LoKITTIregistration recall (%): 72.3 -> 69.7 (phi=10)Hurt
combine Finest loss with Positive Variance loss instead of either alone (ablation)GCL+Conv · LoKITTIregistration recall (%): 64.4 (PV) -> 72.3 (F+PV); 53.2 (F) -> 72.3Improved
block gradient on the finest feature (BF) in finest loss (ablation)GCL+Conv · LoKITTIregistration recall (%): 72.1 (F+PP) -> 50.1 (BF+PP)Hurt
different loss designs on moderate-difficulty KITTI [10,10] (ablation)GCL+Conv · KITTI [10,10]registration recall (%): 98.6 to 99.2No clear effect
scale up pair-wise training data by 20x for FCGF instead of using GCL (ablation)FCGF · LoKITTIregistration recall (%): 24.0 -> 28.8 (vs GCL 72.3)No clear effect
use non-i.i.d. correlated positive pairs (PCL) rather than group positivesfeature extractor training · feature drift analysisfeature driftHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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