AI Paper Atlas

Research map / Point clouds / Registration and matching

Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching

Yue Pan, Tao Sun, Liyuan Zhu, Lucas Nunes, Iro Armeni, Jens Behley, Cyrill Stachniss

ECCV 2026 · Point clouds › Registration and matching · approach: Learned feature-based registration · 10 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 test-time rigidity forcing (ablation)RAP · Cross-domain multi-view benchmark edgesuccess rate (%): 83.57 -> 85.92Improved
add test-time rigidity forcing (ablation)RAP · Cross-domain multi-view benchmark graphsuccess rate (%): 72.88 -> 77.31Improved
add test-time rigidity forcing (ablation)RAP · 3DLoMatchsuccess rate (%): 74.63 -> 78.78Improved
use 10-step Euler integration instead of 1 step (ablation)RAP · Cross-domain multi-view benchmark graphsuccess rate (%): 50.32 -> 77.31Improved
use 10-step Euler integration instead of 1 step (ablation)RAP · 3DLoMatchsuccess rate (%): 61.05 -> 78.78Improved
add local descriptor features as conditions (ablation)RAP · Cross-domain multi-view benchmark edgesuccess rate (%): 43.07 -> 85.92Improved
add local descriptor features as conditions (ablation)RAP · 3DLoMatchsuccess rate (%): 50.05 -> 78.78Improved
increase transformer blocks from 8 to 10 (ablation)RAP · Cross-domain multi-view benchmark edgesuccess rate (%): 81.08 -> 85.92Improved
increase transformer blocks from 6 to 10 (ablation)RAP · Cross-domain multi-view benchmark edgesuccess rate (%): 65.64 -> 85.92Improved
retrain BUFFER-X on RAP's extended training dataBUFFER-X+PGO · Cross-domain multi-view benchmark edgesuccess rate (%): 50.4 -> 57.7Improved
replace pairwise+PGO pipeline with single-stage RAPBUFFER-X*+PGO · Cross-domain multi-view benchmark graphsuccess rate (%): 36.5 -> 77.3Improved
replace two-stage pipeline with RAPBUFFER-X*+PGO · Cross-domain multi-view benchmarkruntime (s): 36.0 -> 8.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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