Adaptive estimation of optimal color transformations for deep convolutional network based homography estimation
- Resource Type
- Authors
- Rafael Marcos Luque-Baena; Ezequiel López-Rubio; Miguel A. Molina-Cabello; Jorge García-González; Karl Thurnhofer-Hemsi
- Source
- ICPR
- Subject
- Artificial neural network
Computer science
business.industry
Deep learning
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Estimator
020207 software engineering
02 engineering and technology
Convolutional neural network
Image (mathematics)
Computer Science::Computer Vision and Pattern Recognition
Pattern recognition (psychology)
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Computer vision
Artificial intelligence
Data pre-processing
business
Homography (computer vision)
- Language
Homography estimation from a pair of natural images is a problem of paramount importance for computer vision. Specialized deep convolutional neural networks have been proposed to accomplish this task. In this work, a method to enhance the result of this kind of homography estimators is proposed. Our approach generates a set of tentative color transformations for the image pair. Then the color transformed image pairs are evaluated by a regressor that estimates the quality of the homography that would be obtained by supplying the transformed image pairs to the homography estimator. Then the image pair that is predicted to yield the best result is provided to the homography estimator. Experimental results are shown, which demonstrate that our approach performs better than the direct application of the homography estimator to the original image pair, both in qualitative and quantitative terms.