Enhanced wide-activated residual network for efficient and accurate image deblocking
| Autor: | Pradeep Karn, Xiaohai He, Zhengxin Chen, Chao Ren, Xiong Shuhua |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Compression artifact
Deblocking filter Computer science 020206 networking & telecommunications 02 engineering and technology computer.file_format Lossy compression Residual JPEG Convolutional neural network Reduction (complexity) Signal Processing 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Electrical and Electronic Engineering computer Algorithm Software Block (data storage) |
| Zdroj: | Signal Processing: Image Communication. 96:116283 |
| ISSN: | 0923-5965 |
| Popis: | To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect