BP-DIP: A Backprojection based Deep Image Prior
| Autor: | Tom Tirer, Jenny Zukerman, Raja Giryes |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Deblurring business.industry Computer science Deep learning Image and Video Processing (eess.IV) Machine Learning (stat.ML) 020206 networking & telecommunications Pattern recognition 02 engineering and technology Electrical Engineering and Systems Science - Image and Video Processing Convolutional neural network Least squares Machine Learning (cs.LG) Image (mathematics) Term (time) Statistics - Machine Learning FOS: Electrical engineering electronic engineering information engineering 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Image restoration |
| Zdroj: | EUSIPCO 2020 28th European Signal Processing Conference (EUSIPCO) |
| DOI: | 10.23919/eusipco47968.2020.9287540 |
| Popis: | Deep neural networks are a very powerful tool for many computer vision tasks, including image restoration, exhibiting state-of-the-art results. However, the performance of deep learning methods tends to drop once the observation model used in training mismatches the one in test time. In addition, most deep learning methods require vast amounts of training data, which are not accessible in many applications. To mitigate these disadvantages, we propose to combine two image restoration approaches: (i) Deep Image Prior (DIP), which trains a convolutional neural network (CNN) from scratch in test time using the given degraded image. It does not require any training data and builds on the implicit prior imposed by the CNN architecture; and (ii) a backprojection (BP) fidelity term, which is an alternative to the standard least squares loss that is usually used in previous DIP works. We demonstrate the performance of the proposed method, termed BP-DIP, on the deblurring task and show its advantages over the plain DIP, with both higher PSNR values and better inference run-time. Comment: Accepted to EUSIPCO 2020. Link to code: https://github.com/jennyzu/BP-DIP-deblurring. 5 pages, 5 figures, 1 table |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|