Explicit Learning Of Feature Orientation Estimation
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)(2019)
Abstract
While many learning-driven algorithms for local feature detection and description have submerged during recent years. One key component in the pipeline, namely orientation estimation, still remains underdeveloped. Among all sorts of difficulties, the impracticality and tedium of finding a "ground truth" feature orientation as a learning target is one big challenge. In this paper, we bypass this "thinking trap" and propose an unsupervised scheme that explicitly trains a simple convolutional neural network to predict orientations for feature points. Together with a carefully designed loss term, the network manages to provide accurate orientation estimations. We further evaluate the capability of this estimator in two experiments: orientation estimation and feature matching. Results showed the proposed method outperforms other compared methods on multiple benchmark datasets. The pre-trained model is publicly available.
MoreTranslated text
Key words
Feature orientation, unsupervised learning, explicit learning, feature matching
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined