Deep Local Feature 文章 & 数据收集

在 SLAM 中 Local Feature 的提取和匹配是一个比较重要的内容,近些年有很多相关的使用 Deep Learning 学习局部描述子的工作,这里做一下相关文章和代码收集。后续如有精力会进行速度和性能比较。

文章收集

文章 会议 PDF 代码
GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints ECCV 2018 PDF Code
DELF: DEep Local Features CVPR 2018 PDF Code
LF-Net: Learning Local Features from Images NIPS 2018 PDF Code
AffNet: Repeatability Is Not Enough: Learning Discriminative Affine Regions via Discriminability ECCV 2018 PDF Code
SuperPoint: Self-Supervised Interest Point Detection and Description CVPR 2018 PDF Code
DeepCD: Learning Deep Complementary Descriptors for Patch Representations ICCV 2017 PDF Code
HardNet: Working hard to know your neighbor’s margins: Local descriptor learning loss NIPS 2017 PDF Code
TFeat: shallow convolutional patch descriptor BMVC 2016 PDF Code
LIFT: Learned Invariant Feature Transform ECCV 2016 PDF Code

数据收集

数据集名称 下载地址
Phototour http://phototour.cs.washington.edu/patches/default.htm
HPatches https://github.com/hpatches/hpatches-dataset

About skylook

增强现实、图像识别技术爱好者。
This entry was posted in CNN. Bookmark the permalink.

发表评论

电子邮件地址不会被公开。




Optimization WordPress Plugins & Solutions by W3 EDGE