AI Paper Atlas

Research map / Point clouds / Registration and matching

FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration

Hao Xu, Nianjin Ye, Guanghui Liu, Bing Zeng, Shuaicheng Liu

AAAI 2022 · Point clouds › Registration and matching · approach: Learned feature-based registration · 77 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 multi-level feature interactions (PFI and GFI) (ablation)FINet · ModelNet40 unseen shapes and categoriesRMSE(R): 4.857 -> 4.023Improved
add PFI to the single-branch setup (ablation)FINet · ModelNet40 ablationRMSE(R): 4.921 -> 4.368Improved
add GFI to the single-branch setup (ablation)FINet · ModelNet40 ablationRMSE(R): 4.921 -> 4.792Improved
add PFI to the dual-branch setup (ablation)FINet · ModelNet40 ablationRMSE(R): 4.857 -> 4.308Improved
add GFI to the dual-branch setup (ablation)FINet · ModelNet40 ablationRMSE(R): 4.857 -> 4.220Improved
combine PFI and GFI rather than using PFI alone (ablation)FINet dual branches · ModelNet40 ablationRMSE(R): 4.308 -> 4.023Improved
add point-wise feature dropout loss (ablation)FINet · ModelNet40 ablationRMSE(R): 4.023 -> 3.902Improved
add transformation sensitivity loss (ablation)FINet · ModelNet40 ablationRMSE(R): 3.902 -> 3.841Improved
use dual branches rather than single branch without additional supervising (ablation)FINet · ModelNet40 ablationRMSE(R): 4.921 -> 4.857Improved
regress saliency points instead of omitting the explicit SP objective (ablation)FINet dual branches · ModelNet40 ablationRMSE(R): 4.023 -> 3.955Improved
add saliency-point regression in the single-branch setup (ablation)FINet single branch · ModelNet40 ablationRMSE(R): 4.427 -> 4.481Hurt
use FINet rather than OMNetModelNet40 unseen shapes · ModelNet40 unseen shapes, OS and TSRMSE(R): 0.771 -> 0.694; 1.384 -> 1.267Improved

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