AI Paper Atlas

Research map / Point clouds / Registration and matching

PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration

Mingzhi Yuan, Kexue Fu, Zhihao Li, Yucong Meng, Manning Wang

ICCV 2023 · Point clouds › Registration and matching · approach: Learned feature-based registration · 29 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
replace unidirectional late fusion with multi-scale bidirectional fusionPointMBF vs LLT · ScanNet (trained on ScanNet)translation accuracy at 5cm: 80.4 -> 83.9Improved
train on 3DMatch and test on unseen ScanNetPointMBF · ScanNet generalizationtranslation accuracy at 5cm: 81.0 vs LLT 76.9Improved
use multi-scale bidirectional fusion instead of direct concatenation (ablation)PointMBF · ScanNet (trained on 3DMatch)translation accuracy at 5cm: 78.5 -> 81.0Improved
use transformer fusion in high-level space instead of bidirectional fusion (ablation)PointMBF · ScanNet (trained on 3DMatch)translation accuracy at 5cm: 81.0 -> 74.7Hurt
add residual design in fusion modules (ablation)PointMBF · ScanNet (trained on 3DMatch)translation accuracy at 5cm: 80.3 -> 81.0Improved
treat depth as an extra input channel of a shared visual network (ablation)UR&R-style visual branch · ScanNet (trained on 3DMatch)translation accuracy at 5cm: 72.4 -> 64.1Hurt
add fusion in encoding stage (ablation)PointMBF with decode and concat · ScanNet (trained on 3DMatch)translation accuracy at 5cm: 80.6 -> 81.0Improved
add fusion in decoding stage (ablation)PointMBF with encode and concat · ScanNet (trained on 3DMatch)translation accuracy at 5cm: 80.5 -> 81.0Improved
add final concatenation to encode+decode bidirectional fusion (ablation)PointMBF · ScanNet (trained on 3DMatch)translation accuracy at 5cm: 80.3 -> 81.0Improved
add geometric-to-visual fusion on top of V2G + CAT (ablation)PointMBF · ScanNet (trained on 3DMatch)translation accuracy at 5cm: 80.3 -> 81.0Improved
add visual-to-geometric fusion on top of G2V + CAT (ablation)PointMBF · ScanNet (trained on 3DMatch)translation accuracy at 5cm: 79.2 -> 81.0Improved
use weaker single branches (visual worse than LLT in rotation, poor geometric branch) with fusionPointMBF · ScanNetregistration accuracyImproved

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