Method and apparatus with image correspondence
AssigneesSamsung Electronics Co., Ltd., Postech Research and Business Development Foundation
InventorsSeungju HAN, Minsu CHO, Juhong MIN, Jongmin LEE, Changbeom PARK
Life of this patent
Estimating the term…
Abstract
A method with image correspondence includes: acquiring a plurality of feature map pairs corresponding to outputs of a plurality of layers of a convolutional neural network (CNN) in response to an input of an input image pair; selecting a portion of feature map pairs from among the plurality of feature map pairs based on a feature of each of the plurality of feature map pairs; generating a hyper feature map pair based on the selected portion of feature map pairs; and generating a correspondence result of the input image pair based on a correlation of the hyper feature map pair.
Claims26
A method with image correspondence, comprising:
- acquiring a plurality of feature map pairs corresponding to outputs of a plurality of layers of a convolutional neural network (CNN) in response to an input of an input image pair;
- selecting a portion of feature map pairs from among the plurality of feature map pairs based on a feature of each of the plurality of feature map pairs;
- generating a hyper feature map pair based on the selected portion of feature map pairs;
- and
- generating a correspondence result of the input image pair based on a correlation of the hyper feature map pair.
An apparatus with image correspondence, comprising:
- a processor configured to
- acquire a plurality of feature map pairs corresponding to outputs of a plurality of layers of a convolutional neural network (CNN) in response to an input of an input image pair,
- select a portion of feature map pairs from among the plurality of feature map pairs based on a feature of each of the plurality of feature map pairs,
- generate a hyper feature map pair based on the selected portion of feature map pairs, and
- generate a correspondence result of the input image pair based on a correlation of the hyper feature map pair.
An electronic device comprising:
- a camera configured to generate one or more input images of an input image pair;
- and
- a processor configured to
- acquire a plurality of feature map pairs corresponding to outputs of a plurality of layers of a convolutional neural network (CNN) in response to an input of the input image pair,
- select a portion of feature map pairs from among the plurality of feature map pairs based on a feature of each of the plurality of feature map pairs,
- generate a hyper feature map pair based on the selected portion of feature map pairs, and
- generate a correspondence result of the input image pair based on a correlation of the hyper feature map pair.
A method with image correspondence, comprising:
- determining, using one or more neural networks, relevance vectors of feature map pairs output from intermediate convolutional neural network (CNN) layers, wherein the feature map pairs are generated based on an image pair;
- dynamically selecting, based on the relevance vectors, a portion of the feature map pairs for generating a hyper feature map pair;
- and
- generating a correspondence result of the image pair based on a correlation of the hyper feature map pair.
Dependencies are inferred from the claim text.