AI Paper Atlas

Research map / Point clouds / Registration and matching

RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration

Jiuming Liu, Guangming Wang, Zhe Liu, Chaokang Jiang, Marc Pollefeys, Hesheng Wang

ICCV 2023 · Point clouds › Registration and matching · approach: Robust inlier selection for registration · 91 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
iteratively refine pose through finer layers instead of outputting from coarsest layer (ablation)RegFormer · KITTI odometryRegistration recall: 64.2% -> 99.8%Improved
add projection mask to transformer attention (ablation)RegFormer · KITTI odometryRegistration recall: 98.1% -> 99.8%Improved
use point Swin transformer instead of 2D CNN for feature extraction (ablation)RegFormer · KITTI odometryRegistration recall: 82.2% -> 99.8%Improved
use point Swin transformer instead of PointNet++ (ablation)RegFormer · KITTI odometryRegistration recall: 92.4% -> 99.8%Improved
add cross-attention in bijective association transformer (ablation)RegFormer · KITTI odometryRegistration recall: 98.7% -> 99.8%Improved
add all-to-all point gathering at coarsest layer (ablation)RegFormer · KITTI odometryRegistration recall: 63.3% -> 99.8%Improved
use BAT instead of cost volume association (ablation)RegFormer · KITTI odometryRegistration recall: 93.4% -> 99.8%Improved
RegFormer vs RANSAC on KITTI recall and runtimeRegFormer · KITTI odometryRegistration recall: 91.9% -> 99.8%Improved
RegFormer vs Predator on RTE under 10m-apart pairsRegFormer · KITTI (pairs at least 10m apart)RTE (cm): 6.8 -> 8.4Hurt
RegFormer vs HRegNet on NuScenes translation errorRegFormer · NuScenesRTE (m): RTE 0.18 -> 0.20; RRE 0.45 -> 0.22Mixed

Later papers that compared with this method

1 later accepted paper reports Regformer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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