AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Two-View Correspondences and Geometry Using Order-Aware Network

Jiahui Zhang, Dawei Sun, Zixin Luo, Anbang Yao, Lei Zhou, Tianwei Shen, Yurong Chen, Long Quan, Hongen Liao

ICCV 2019 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 396 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 Order-Aware DiffPool/DiffUnpool layers (UnB) (ablation)PointCN · YFCC100M outdoor unknown, no RANSACmAP5: 23.55 -> 28.78Improved
add plain DiffUnpool layers (UnA) (ablation)PointCN · YFCC100M outdoor unknown, no RANSACmAP5: 23.55 -> 24.10No clear effect
use Order-Aware DiffUnpool instead of plain DiffUnpool (ablation)PointCN + pooling · YFCC100M outdoor unknown, no RANSACmAP5: 24.10 -> 28.78Improved
replace PointCN blocks at second level with Order-Aware Filtering blocks (ablation)PointCN + UnB · YFCC100M outdoor unknown, no RANSACmAP5: 28.78 -> 32.55Improved
use larger three-level model (ablation)Order-Aware Network · YFCC100M outdoor unknown, no RANSACmAP5: 32.55 -> 30.48Hurt
use geometry loss instead of L2 loss (ablation)Order-Aware Network · YFCC100M outdoor unknownmAP5: 51.63 -> 51.10 with RANSAC; 32.55 -> 33.68 withoutMixed
add iterative network (ablation)Order-Aware Network + geometry loss · YFCC100M outdoor unknown, no RANSACmAP5: 33.68 -> 39.33Improved
lower RANSAC inlier threshold from 0.01 to 0.001 (ablation)PointCN · YFCC100M outdoor unknown, with RANSACmAP5: 17.53 -> 44.50Improved
train on 68 sequences instead of 2 (ablation)PointCN · YFCC100M outdoor unknown, with RANSACmAP5: 44.50 -> 47.98Improved
use SuperPoint instead of SIFT features (ablation)PointCN · YFCC100M outdoor unknown, with RANSACmAP5: 47.98 -> 43.18Hurt
Order-Aware Network versus PointCNPointCN · YFCC100M outdoor unknown, no RANSACmAP5: 23.55 -> 32.55Improved

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