English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The local feature detector and descriptor are essential in many computervision tasks, such as SLAM and 3D reconstruction. In this paper, we introducetwo separate CNNs, lightweight SobelNet and DesNet, to detect key points and tocompute dense local descriptors. The detector and the descriptor work inparallel. Sobel filter provides the edge structure of the input images as theinput of CNN. The locations of key points will be obtained after exerting thenon-maximum suppression (NMS) process on the output map of the CNN. We designGaussian loss for the training process of SobelNet to detect corner points askeypoints. At the same time, the input of DesNet is the original grayscaleimage, and circle loss is used to train DesNet. Besides, output maps ofSobelNet are needed while training DesNet. We have evaluated our method onseveral benchmarks including HPatches benchmark, ETH benchmark, and FM-Bench.SobelNet achieves better or comparable performance with less computationcompared with SOTA methods in recent years. The inference time of an image of640x480 is 7.59ms and 1.09ms for SobelNet and DesNet respectively on RTX 2070SUPER.

Realtime CNN-based Keypoint Detector with Sobel Filter and CNN-based Descriptor Trained with Keypoint Candidates