AI Paper Atlas

Research map / Point clouds / Registration and matching

CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection

Zhixin Cheng, Jiacheng Deng, Xinjun Li, Xiaotian Yin, Bohao Liao, Baoqun Yin, Wenfei Yang, Tianzhu Zhang

ICCV 2025 · Point clouds › Registration and matching · approach: Learned feature-based registration · 6 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 ICE (image channel enhancement) (ablation)2D3D-MATR · RGB-D Scenes V2RR: 55.8 -> 56.9Improved
add PCE (point cloud channel enhancement) (ablation)2D3D-MATR · RGB-D Scenes V2RR: 55.8 -> 56.0Improved
add ICE and PCE jointly (ablation)2D3D-MATR · RGB-D Scenes V2RR: 55.8 -> 58.2Improved
add CMCF cross-modal channel filtering (ablation)2D3D-MATR · RGB-D Scenes V2PIR: 48.5 -> 59.2Improved
add GOS (optimal transport selection) replacing top-k (ablation)2D3D-MATR · RGB-D Scenes V2IR: 32.5 -> 35.3Improved
add all modules (full CA-I2P) (ablation)2D3D-MATR · RGB-D Scenes V2RR: 55.8 -> 63.3Improved
add IME (ablation)2D3D-MATR · 7-ScenesRR: 75.8 -> 77.3Improved
add CMCF on top of IME (ablation)2D3D-MATR · 7-ScenesRR: 77.3 -> 79.2Improved
add GOS (ablation)2D3D-MATR · 7-ScenesRR: 75.8 -> 76.9Improved
combine IME, CMCF and GOS (ablation)2D3D-MATR · 7-ScenesRR: 75.8 -> 79.5Improved
use all three image enhancement features F_I1, F_I2, F_I3 instead of F_I1 alone (ablation)ICE · RGB-D Scenes V2RR: 55.5 -> 56.9Improved
increase CMCF iterations from 1 to 10 (ablation)CA-I2P · RGB-D Scenes V2RR: 63.3 -> 49.9Hurt

Later papers that compared with this method

3 later accepted papers report CA-I2P as a baseline in their results tables; 3 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 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