RF-Net: An End-to-End Image Matching Network based on Receptive Field.
Xuelun ShenCheng WangXin LiZenglei YuJonathan LiChenglu WenMing ChengZijian HePublished in: CoRR (2019)
Keyphrases
- end to end
- image matching
- receptive fields
- biologically inspired
- natural images
- image representation
- image retrieval
- relevance feedback
- image registration
- space time
- computer vision
- matching algorithm
- keypoints
- input space
- object recognition
- primary visual cortex
- hidden layer
- congestion control
- saliency map
- image matching method
- visual information
- real time
- feed forward
- higher order
- image analysis
- multiscale
- data sets