Research map / Image generation / Autoregressive and latent generation
Comparative Evaluation of Hand-Crafted and Learned Local Features
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use advanced hand-crafted descriptors instead of learned descriptors | local feature matching · Heinly descriptor benchmark, across transformations | matching performance | Mixed |
| Use learned descriptors rather than standard SIFT | local feature matching · Heinly descriptor benchmark | Recall | Helped |
| Use standard SIFT rather than learned descriptors | local feature matching · Heinly descriptor benchmark | Precision | Helped |
| Use DSP-SIFT rather than SIFT | image-based reconstruction · Internet photo datasets | sparse reconstruction completeness | Helped |
| Use learned descriptors rather than SIFT | image-based reconstruction · Fountain, Herzjesu, and South Building | reconstruction quality | No clear effect |
| Use learned descriptors rather than SIFT | image-based reconstruction · large-scale Internet photo collections | reconstruction completeness and accuracy | Mixed |
| Train learned descriptors on more data | learned local feature descriptors · varied image transformations and applications | performance consistency | Helped |
Closest papers by meaning
- HPatches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors (CVPR 2017 · similarity 0.90)
- Local Descriptors Optimized for Average Precision (CVPR 2018 · similarity 0.89)
- OmniGlue: Generalizable Feature Matching with Foundation Model Guidance (CVPR 2024 · similarity 0.84)
- XFeat: Accelerated Features for Lightweight Image Matching (CVPR 2024 · similarity 0.84)
- ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses (NeurIPS 2024 · similarity 0.84)
- MATCHA: Towards Matching Anything (CVPR 2025 · 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.