AI Paper Atlas

Research map / 3D vision / Depth and stereo

LF-Net: Learning Local Features from Images

Yuki Ono, Eduard Trulls, Pascal Fua, Kwang Moo Yi

NeurIPS 2018 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 348 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
Disable rotation and scale estimationLF-Net · Outdoors datasetmatching score: .321 -> .406Improved
Disable rotation and scale estimationLF-Net · Indoors datasetmatching score: .450 -> .511Improved
Add patch-wise loss to detector training (jointly train detector and descriptor) (ablation)LF-Net w/ rot-scl · Outdoors datasetmatching score: .299 to .321Improved
Add patch-wise loss to detector training (jointly train detector and descriptor) (ablation)LF-Net w/ rot-scl · Indoors datasetmatching score: .445 to .450Improved
Add rotation and scale augmentations and estimationLF-Net · Outdoors dataset, rotated image pairsaverage matching score: .074 -> .338Improved
Train on outdoors data and test on indoors dataLF-Net · Indoors datasetmatching score: .450 to .370Hurt
Train on indoors data and test on outdoors dataLF-Net · Outdoors datasetmatching score: .321 to .295Hurt

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