AI Paper Atlas

Research map / Point clouds / Registration and matching

FS-I2P: A Hierarchical Focus–Sweep Registration Network with Dynamically Allocated Depth

Zhixin Cheng, Yujia Chen, Xujing Tao, Bohao Liao, Xiaotian Yin, Baoqun Yin, Tianzhu Zhang

ICML 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 Sweep module to HTS baseline (ablation)FS-I2P · RGB-D Scenes V2RR: 56.4 -> 62.4Improved
add Focus on top of Sweep + HTS (ablation)FS-I2P · RGB-D Scenes V2RR: 62.4 -> 68.2Improved
add Focus without Sweep (ablation)FS-I2P · RGB-D Scenes V2RR: 56.4 -> 59.7Improved
add Dynamic Layer Allocation Strategy (ablation)FS-I2P · RGB-D Scenes V2RR: 68.2 -> 72.9Improved
add hierarchical top-k selection (ablation)FS-I2P · RGB-D Scenes V2RR: 56.2 -> 72.9Improved
remove all modules including HTS (ablation)FS-I2P · RGB-D Scenes V2RR: 56.4 -> 49.5Hurt
stack more transformer cross-attention layers (ablation)Transformer interaction · image-point MMDMMD: improves then rises with depthMixed
use DINOv2 image encoderFS-I2P · RGB-D Scenes V2RR: 72.9 -> 86.3Improved
use DINOv2 image encoderFS-I2P · 7-ScenesRR: 82.7 -> 84.6Improved
use Mamba-based Focus-Sweep instead of transformer interactionFS-I2P · efficiencyinference time and memory: 0.497 s -> 0.304 s; 8346 -> 6415 MBImproved
use FS-I2P instead of Diff2I2P on 7-ScenesFS-I2P · 7-ScenesRR: 83.0 vs 82.7Hurt

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