AI Paper Atlas

Research map / 3D vision / Depth and stereo

Single-Image Depth Prediction Makes Feature Matching Easier

Carl Toft, Daniyar Turmukhambetov, Torsten Sattler, Fredrik Kahl, Gabriel J. Brostow

ECCV 2020 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 24 citations (OpenAlex)

Read the paper

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
extract features from depth-based perspectively rectified planes instead of original imagesSIFT and BRISK · Own dataset, relative-pose success within 5 degfraction of image pairs localizedImproved
extract features from rectified imagesSuperPoint · Own dataset, relative-pose successfraction of image pairs localizedNo clear effect
extract features from rectified imagesORB · Own dataset, relative-pose successfraction of image pairs localizedMixed
unwarp the ground plane before SIFT matchingSIFT on RobotCar Alternate Route, 180 deg viewpoint change · Oxford RobotCar Alternate Routepercentage of localized queriesImproved

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