Single-Image Camera Response Function Using Prediction Consistency and Gradual Refinement
| Autor: | Loong-Fah Cheong, Aashish Sharma, Robby T. Tan |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
business.industry Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition 02 engineering and technology Real image 01 natural sciences Image (mathematics) 010309 optics Consistency (database systems) Noise Simple (abstract algebra) 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Single image CRFS business |
| Zdroj: | Computer Vision – ACCV 2020 ISBN: 9783030695439 ACCV (6) |
| DOI: | 10.1007/978-3-030-69544-6_2 |
| Popis: | A few methods have been proposed to estimate the CRF from a single image, however most of them tend to fail in handling general real images. For instance, EdgeCRF based on patches extracted from colour edges works effectively only when the presence of noise is insignificant, which is not the case for many real images; and, CRFNet, a recent method based on fully supervised deep learning works only for the CRFs that are in the training data, and hence fail to deal with other possible CRFs beyond the training data. To address these problems, we introduce a non-deep-learning method using prediction consistency and gradual refinement. First, we rely more on the patches of the input image that provide more consistent predictions. If the predictions from a patch are more consistent, it means that the patch is likely to be less affected by noise or any inferior colour combinations, and hence, it can be more reliable for CRF estimation. Second, we employ a gradual refinement scheme in which we start from a simple CRF model to generate a result which is more robust to noise but less accurate, and then we gradually increase the model’s complexity to improve the estimation. This is because a simple model, while being less accurate, overfits less to noise than a complex model does. Our experiments confirm that our method outperforms the existing single-image methods for both daytime and nighttime real images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|