AI Paper Atlas

Research map / 3D vision / Depth and stereo

ConvMatch: Rethinking Network Design for Two-View Correspondence Learning

Shihua Zhang, Jiayi Ma

AAAI 2023 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 36 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
Use ConvMatch's motion-field regularization and CNN rectification frameworkTwo-view correspondence learning · YFCC100M outdoor relative pose, with RANSACAUC@5°: 31.55 -> 31.69Improved
Use ConvMatch's motion-field regularization and CNN rectification frameworkTwo-view correspondence learning · YFCC100M outdoor relative pose, without RANSACAUC@10°: 44.69 -> 49.14Improved
Use ConvMatch's motion-field regularization and CNN rectification frameworkTwo-view correspondence learning · SUN3D indoor relative pose, with RANSACAUC@20°: 33.47 -> 34.41Improved
Use ConvMatch's motion-field regularization and CNN rectification frameworkTwo-view correspondence learning · SUN3D indoor relative pose, without RANSACAUC@20°: 37.15 -> 40.49Improved
Use ConvMatch for homography estimationTwo-view correspondence learning · HPatches homography estimationAcc.: 72.93 -> 73.45Improved
Use ConvMatch for homography estimationTwo-view correspondence learning · HPatches homography estimationF-score: 85.44 -> 83.80Hurt
Classify unordered correspondences directly rather than regularizing and rectifying motion vectors (ablation)ConvMatch · YFCC100M outdoor relative pose, with RANSACAUC@20°: 68.45 -> 65.92Hurt
Replace the CNN backbone with an MLP and Context Normalization (ablation)ConvMatch · YFCC100M outdoor relative pose, with RANSACAUC@20°: 68.45 -> 66.21Hurt
Replace the simple CNN backbone with UNet (ablation)ConvMatch · YFCC100M outdoor relative pose, with RANSACAUC@20°: 68.45 -> 69.96Improved
Increase the number of rectifying layers from L = 6 to L = 8 (ablation)ConvMatch · YFCC100M outdoor relative pose, without RANSACAUC@20°: 67.91 -> 68.89Improved
Increase the grid number from K = 16 to K = 24 (ablation)ConvMatch · YFCC100M outdoor relative pose, without RANSACAUC@20°: 67.91 -> 67.94No clear effect

Later papers that compared with this method

3 later accepted papers report ConvMatch+ as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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