AI Paper Atlas

Research map / 3D vision / Depth and stereo

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

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

TPAMI 2020 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 40 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 plain DiffUnpool layer (ablation)PointCN baseline · YFCC100M unknown, without RANSACmAP@5: 23.55 -> 24.10No clear effect
add Order-Aware DiffUnpool layer (ablation)PointCN baseline · YFCC100M unknown, without RANSACmAP@5: 23.55 -> 28.78Improved
replace PointCN blocks with Order-Aware Filtering blocks at second level (ablation)PointCN + UnB · YFCC100M unknown, without RANSACmAP@5: 28.78 -> 32.55Improved
use larger three-level U-Net model (ablation)PointCN + UnB + OF · YFCC100M unknown, without RANSACmAP@5: 32.55 -> 30.48Hurt
use geometry loss instead of L2 loss (ablation)PointCN + UnB + OF · YFCC100M unknown, without RANSACmAP@5: 32.55 -> 33.68Improved
add iterative refinement network (ablation)PointCN + UnB + OF + Geo · YFCC100M unknown, without RANSACmAP@5: 33.68 -> 39.33Improved
lower RANSAC inlier threshold from 0.01 to 0.001 (ablation)PointCN baseline · YFCC100M unknown, with RANSACmAP@5: 17.53 -> 44.50Improved
train on 68 sequences instead of 2 (ablation)PointCN baseline · YFCC100M unknown, with RANSACmAP@5: 44.50 -> 47.98Improved
use OANet instead of PointCNOANet · YFCC100M outdoor unknown, without RANSACmAP@5: 23.55 -> 39.33Improved
use OANet++ instead of PointCNOANet++ · SUN3D indoor unknown, without RANSACmAP@5: 9.36 -> 16.39Improved

Later papers that compared with this method

4 later accepted papers report OANet as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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