A study on the impact of training data in CNN-based super-resolution for low bitrate end-to-end video coding
| Autor: | Gildas Cocherel, Nicolas Dhollande, Wassim Hamidouche, Fatemeh Nasiri, Luce Morin |
|---|---|
| Přispěvatelé: | Institut de Recherche Technologique b-com (IRT b-com), Institut d'Électronique et des Technologies du numéRique (IETR), Université de Nantes (UN)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Institut National des Sciences Appliquées (INSA), AVIWEST, Nantes Université (NU)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Université de Nantes (UN)-Université de Rennes 1 (UR1) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Compression artifact
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Convolutional neural network 03 medical and health sciences 0302 clinical medicine End-to-end principle [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing 0202 electrical engineering electronic engineering information engineering [INFO]Computer Science [cs] ComputingMilieux_MISCELLANEOUS Training set Pixel business.industry Quantization (signal processing) Convolutional Neural Networks Pattern recognition 030229 sport sciences Superresolution Uncompressed video Low Bitrate Video Coding 020201 artificial intelligence & image processing Artificial intelligence business Super Resolution Coding (social sciences) |
| Zdroj: | Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA) Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA), Nov 2020, Paris, France. pp.1-5, ⟨10.1109/IPTA50016.2020.9286717⟩ 2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA) 2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA), Nov 2020, Paris, France. pp.1-5, ⟨10.1109/IPTA50016.2020.9286717⟩ IPTA |
| Popis: | International audience; In this study, the effectiveness of Super Resolution (SR) methods based on Convolutional Neural Network (CNN) in low bitrate video coding, with a focus on the Versatile Video Coding Standard (VVC), is investigated. Video transmission over networks with limited bandwidth is a common challenge for different applications. One solution is to adopt SR methods where the main principle is to spatially downsample the input sequence prior to the encoding, then up-sampling the decoded sequence before displaying it. For a fixed target bandwidth, a finer quantization is applied on the low-resolution sequence compared to high-resolution, so that the high quality reconstructed pixels help in retrieving the lost information. However, most CNN-based SR methods are designed for single images and merely focus on the original input signal. Therefore, their trained networks lack understanding of compression artifacts. In this study, we test a hypothesis that training CNN-based SR methods with compressed sequences outperforms training with uncompressed ones. The assumption is that such training allows the SR methods to learn compression artifacts and differentiate them from actual texture information. To this end, stateof-the-art CNN-based SR methods are tested with compressed and uncompressed training set. Experiments show that the use of compressed training data brings, on average, an additional bitrate saving of 6%, in terms of BD-Rate. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|