An efficient deep convolutional neural networks model for compressed image deblocking

Li, Ke; Bare, Bahetiyaer; Yan, Bo

doi:10.1109/icme.2017.8019416

Cited by 56 publications

(49 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, extensive works [11], [12], [13], [14], [15], [16], [17], [18], [19], [20], [21], [22], [23] have focused on enhancing the visual quality of compressed image. Specifically, Foi et al [12] applied point-wise Shape-Adaptive DCT (SA-DCT) to reduce the blocking and ringing effects caused by JPEG compression.…”

Section: Related Work On Quality Enhancementmentioning

confidence: 99%

See 1 more Smart Citation

MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video

Guan

Xing

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

164

190

View full text Add to dashboard Cite

The past few years have witnessed great success in applying deep learning to enhance the quality of compressed image/video. The existing approaches mainly focus on enhancing the quality of a single frame, not considering the similarity between consecutive frames. Since heavy fluctuation exists across compressed video frames as investigated in this paper, frame similarity can be utilized for quality enhancement of low-quality frames given their neighboring high-quality frames. This task is Multi-Frame Quality Enhancement (MFQE). Accordingly, this paper proposes an MFQE approach for compressed video, as the first attempt in this direction. In our approach, we firstly develop a Bidirectional Long Short-Term Memory (BiLSTM) based detector to locate Peak Quality Frames (PQFs) in compressed video. Then, a novel Multi-Frame Convolutional Neural Network (MF-CNN) is designed to enhance the quality of compressed video, in which the non-PQF and its nearest two PQFs are the input. In MF-CNN, motion between the non-PQF and PQFs is compensated by a motion compensation subnet. Subsequently, a quality enhancement subnet fuses the non-PQF and compensated PQFs, and then reduces the compression artifacts of the non-PQF. Also, PQF quality is enhanced in the same way. Finally, experiments validate the effectiveness and generalization ability of our MFQE approach in advancing the state-of-the-art quality enhancement of compressed video.

show abstract

Section: Related Work On Quality Enhancementmentioning

confidence: 99%

“…In addition, the structural similarity (SSIM) index is also evaluated. Then, the performance of our MFQE approach is compared with those of AR-CNN [17], DnCNN [20], Li et al [21], DCAD [35] and DS-CNN [25]. Quality enhancement on non-PQFs.…”

Section: Performance Of Our Mfqe Approachmentioning

confidence: 99%

MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video

Guan

Xing

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

164

190

View full text Add to dashboard Cite

show abstract

“…Now, we evaluate the quality enhancement performance of our QG-ConvLSTM approach in terms of ∆PSNR, which measures the PSNR improvement after enhancing the compressed video. Our performance is compared with the state-of-the-art image enhancement methods 2 , including AR-CNN [4], Li et al [8] and DnCNN [7], and video enhancement methods of DCAD [11], QE-CNN [13] and MF-CNN [15]. Table 1 shows the average ∆PSNR results for all test sequences.…”

Section: Performance Of Our Qg-convlstm Approachmentioning

confidence: 99%

“…During the past decade, an increasing number of works have focused on the quality enhancement of compressed image 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 192 193 194 195 196 197 198 199 and video. Most of them [1,2,3,4,5,6,7,8,9] aim at improving the visual quality of JPEG image. Specifically, [1,2,3] utilized non-deep-learning methods for JPEG restoration.…”

Section: Introductionmentioning

confidence: 99%

Quality-Gated Convolutional Lstm for Enhancing Compressed Video

Yang

Sun

et al. 2019

2019 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

The past decade has witnessed great success in applying deep learning to enhance the quality of compressed video. However, the existing approaches aim at quality enhancement on a single frame, or only using fixed neighboring frames. Thus they fail to take full advantage of the inter-frame correlation in the video. This paper proposes the Quality-Gated Convolutional Long Short-Term Memory (QG-ConvLSTM) network with bi-directional recurrent structure to fully exploit the advantageous information in a large range of frames. More importantly, due to the obvious quality fluctuation among compressed frames, higher quality frames can provide more useful information for other frames to enhance quality. Therefore, we propose learning the "forget" and "input" gates in the ConvLSTM cell from quality-related features. As such, the frames with various quality contribute to the memory in ConvLSTM with different importance, making the information of each frame reasonably and adequately used. Finally, the experiments validate the effectiveness of our QG-ConvLSTM approach in advancing the state-of-the-art quality enhancement of compressed video, and the ablation study shows that our QG-ConvLSTM approach is learnt to make a trade-off between quality and correlation when leveraging multi-frame information. The project page: https://github.com/ ryangchn/QG-ConvLSTM.git

show abstract

“…Recently, excellent results were obtained by deep learning-based approaches [1,3,5,8,9,10,19,27,34]. Dong et al [5] developed a shallow CNN for compression artifacts reduction on the basis of the network for superresolution [6].…”

Section: Related Workmentioning

confidence: 99%

DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images

Chen

Qing

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

JPEG is one of the widely used lossy compression methods. JPEG-compressed images usually suffer from compression artifacts including blocking and blurring, especially at low bit-rates. Soft decoding is an effective solution to improve the quality of compressed images without changing codec or introducing extra coding bits. Inspired by the excellent performance of the deep convolutional neural networks (CNNs) on both low-level and high-level computer vision problems, we develop a dual pixel-wavelet domain deep CNNs-based soft decoding network for JPEGcompressed images, namely DPW-SDNet. The pixel domain deep network takes the four downsampled versions of the compressed image to form a 4-channel input and outputs a pixel domain prediction, while the wavelet domain deep network uses the 1-level discrete wavelet transformation (DWT) coefficients to form a 4-channel input to produce a DWT domain prediction. The pixel domain and wavelet domain estimates are combined to generate the final soft decoded result. Experimental results demonstrate the superiority of the proposed DPW-SDNet over several state-ofthe-art compression artifacts reduction algorithms.

show abstract

An efficient deep convolutional neural networks model for compressed image deblocking

Cited by 56 publications

References 13 publications

MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video

MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video

Quality-Gated Convolutional Lstm for Enhancing Compressed Video

DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images

Contact Info

Product

Resources

About