Research map / 3D vision / Depth and stereo
LF-Net: Learning Local Features from Images
Yuki Ono, Eduard Trulls, Pascal Fua, Kwang Moo Yi
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Disable rotation and scale estimation | LF-Net · Outdoors dataset | matching score: .321 -> .406 | Improved |
| Disable rotation and scale estimation | LF-Net · Indoors dataset | matching score: .450 -> .511 | Improved |
| Add patch-wise loss to detector training (jointly train detector and descriptor) (ablation) | LF-Net w/ rot-scl · Outdoors dataset | matching score: .299 to .321 | Improved |
| Add patch-wise loss to detector training (jointly train detector and descriptor) (ablation) | LF-Net w/ rot-scl · Indoors dataset | matching score: .445 to .450 | Improved |
| Add rotation and scale augmentations and estimation | LF-Net · Outdoors dataset, rotated image pairs | average matching score: .074 -> .338 | Improved |
| Train on outdoors data and test on indoors data | LF-Net · Indoors dataset | matching score: .450 to .370 | Hurt |
| Train on indoors data and test on outdoors data | LF-Net · Outdoors dataset | matching score: .321 to .295 | Hurt |
Closest papers by meaning
- Single-Image Depth Prediction Makes Feature Matching Easier (ECCV 2020 · similarity 0.86)
- PPFNet: Global Context Aware Local Features for Robust 3D Point Matching (CVPR 2018 · similarity 0.86)
- LightGlue: Local Feature Matching at Light Speed (ICCV 2023 · similarity 0.85)
- Non-Local Neural Networks (CVPR 2018 · similarity 0.85)
- Video Object Detection with Locally-Weighted Deformable Neighbors (AAAI 2019 · similarity 0.85)
- ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses (NeurIPS 2024 · similarity 0.84)
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.
