AI Paper Atlas

Research map / Point clouds / Point cloud classification

P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching

Bing Wang, Changhao Chen, Zhaopeng Cui, Jie Qin, Chris Xiaoxuan Lu, Zhengdi Yu, Peijun Zhao, Zhen Dong, Fan Zhu, Niki Trigoni, Andrew Markham

ICCV 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 80 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 jointly learned detector (vs no detector, random keypoints) (ablation)P2-Net · 7Scenes pixel-point matching (Stairs)Feature Matching Recall (%): 15.0 -> 88.8Improved
use proposed batch-hard detector instead of SIFT keypoints (ablation)P2-Net · 7Scenes pixel-point matching (Stairs)Feature Matching Recall (%): 15.8 -> 88.8Improved
use proposed detector instead of D2-Net detector (ablation)P2-Net · 7Scenes pixel-point matching (Stairs)Feature Matching Recall (%): 74.3 -> 88.8Improved
use proposed detector instead of D3Feat detector (ablation)P2-Net · 7Scenes pixel-point matching (Stairs)Feature Matching Recall (%): 17.8 -> 88.8Improved
use detector-guided keypoints at test instead of random sampling (ablation)P2-Net · 7Scenes pixel-point matching (Stairs)Registration Recall (%): 74.3 -> 82.6Improved
add ultra-wide reception 2D extractor (vs R2D2 network) (ablation)P2-Net · 7Scenes pixel-point matching (Stairs)Feature Matching Recall (%): 16.2 -> 88.8Improved
add ultra-wide reception 2D extractor (vs R2D2 network) (ablation)P2-Net · 7Scenes pixel-point matching (Stairs)Keypoint Repeatability (%): 33.1 -> 48.1Improved
add ultra-wide reception 2D extractor (vs ASL network) (ablation)P2-Net · 7Scenes pixel-point matching (Stairs)Registration Recall (%): 38.2 -> 82.6Improved
use circle-guided descriptor loss instead of D2-Net triplet lossD2-Net · HPatches (viewpoint)Recall @3px: 0.382 -> 0.413Improved
use P2-Loss instead of contrastive lossASLFeat · HPatches (viewpoint)Recall @3px: 0.583 -> 0.625Improved
use P2-Loss instead of D2-Net triplet loss under illumination changeD2-Net · HPatches (illumination)Recall @3px: 0.564 -> 0.560No clear effect
use P2-Loss instead of contrastive loss under illumination changeASLFeat · HPatches (illumination)HEstimation: 0.919 -> 0.915No clear effect

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