AI Paper Atlas

Research map / Point clouds / Registration and matching

OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration

Pei An, Jiaqi Yang, Yulong Wang, Quan Siwen, Liangliang Nan

ECCV 2026 · Point clouds › Registration and matching · approach: Learned feature-based registration · 0 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 OCA moduleMatr · 7-ScenesRegistration recall: 0.472 -> 0.552Improved
add OCA instead of just extra training (Ref) (ablation)Matr · 7-ScenesRegistration recall: 0.501 -> 0.552Improved
add OCA instead of just extra training (Ref) (ablation)Flow-I2P · 7-ScenesInlier ratio: 0.459 -> 0.530Improved
add OCA module on TUM fine-tuningMatr · TUMRegistration recall: 0.472 -> 0.705Improved
add OCA module on TUM fine-tuningLDF-I2P · TUMRegistration recall: 0.636 -> 0.764Improved
add OCA to CA-I2P on ScanNet (ablation)CA-I2P · ScanNet (fine-tuned)Registration recall: 0.739 -> 0.743Improved
insert OCA without fine-tuning (Zero-OCA) in zero-shotFlow-I2P · ScanNet (zero-shot)Registration recall: 0.263 -> 0.414Improved
insert OCA without fine-tuning (Zero-OCA) in zero-shotFlow-I2P · ScanNet (zero-shot)Inlier ratio: 0.310 -> 0.210Hurt
increase iterations T from 1 to 4 (ablation)Matr+OCA · 7-ScenesInlier ratio: 0.571 -> 0.433Hurt
increase iterations T from 1 to 4 (ablation)Matr+OCA · 7-ScenesRegistration recall: 0.489 -> 0.575Improved
increase iterations T to 5 (ablation)Matr+OCA · 7-ScenesRegistration recall: 0.575 -> 0.539Hurt
increase time step tau from 0.10 to 0.25 (ablation)Matr+OCA · 7-ScenesRegistration recall: 0.552 -> 0.494Hurt

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