Adaptive non-local means filter for image deblocking

Wang, Ci; Zhou, Jun; Liu, Shu

doi:10.1016/j.image.2013.01.006

Cited by 61 publications

(29 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table VII, the compared methods are as follows: (1) VRCNN (S) [18] which is a baseline CNN-based compressed-video post-processing method; (2) QECNN-P [20] which is a compressed-video post-processing method for P frames in HEVC; (3) DRN [21], which is another state-ofthe-art compressed-video post-processing method. (4) VR-CNN+MM+AF (S ), which integrates our partition-awarebased approach into the existing baseline VRCNN method; (5) DRN+MM+AF, which integrates our partition-awarebased approach into the existing DRN method; (6) Our 2-in+MM+AF (D ), which is the full version of our partitionaware-based approach with local mean-based mask and addbased fusion; (7) Our ASN@4D , which is the adaptiveswitching scheme with the deep CNN model. From the table, we can observe that: Table VII also shows that our methods can achieve the same or better performance on color channels (U, V) even though training was done on the luminance channel (Y).…”

Section: Results Of Our Adaptive-switching Schemementioning

confidence: 99%

Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC

Lin

Han³

et al. 2020

IEEE Trans. Multimedia

View full text Add to dashboard Cite

This paper addresses neural network based postprocessing for the state-of-the-art video coding standard, High Efficiency Video Coding (HEVC). We first propose a partitionaware Convolution Neural Network (CNN) that utilizes the partition information produced by the encoder to assist in the post-processing. In contrast to existing CNN-based approaches, which only take the decoded frame as input, the proposed approach considers the coding unit (CU) size information and combines it with the distorted decoded frame such that the artifacts introduced by HEVC are efficiently reduced. We further introduce an adaptive-switching neural network (ASN) that consists of multiple independent CNNs to adaptively handle the variations in content and distortion within compressedvideo frames, providing further reduction in visual artifacts. Additionally, an iterative training procedure is proposed to train these independent CNNs attentively on different local patch-wise classes. Experiments on benchmark sequences demonstrate the effectiveness of our partition-aware and adaptiveswitching neural networks. The project page can be found in

show abstract

Section: Results Of Our Adaptive-switching Schemementioning

confidence: 99%

Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC

Lin

Han³

et al. 2020

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…To the first group belong methods based on traditional image processing techniques working both in the spatial and in the frequency domain. For spatial domain processing different kinds of filters have been proposed, with the intent of restoring specific areas of the images such as edges [3], textures [4], smooth regions [5], etc. Algorithms usually rely on information obtained by the application of the Discrete Cosine Transform (DCT) transform [6].…”

Section: Related Workmentioning

confidence: 99%

“…Comparison on QFs not seen during training. For ARCNN and MWCNN the models trained for QF=10 and QF=20 are tested on QF in the range[5,25]. The proposed model is trained for QF in the range[10, 100] with steps of 10, and is tested on the same intermediate QFs not seen in training.…”

mentioning

confidence: 99%

Deep Residual Autoencoder for Blind Universal JPEG Restoration

2020

View full text Add to dashboard Cite

In this paper we propose a deep residual autoencoder exploiting Residual-in-Residual Dense Blocks (RRDB) to remove artifacts in JPEG compressed images that is independent from the Quality Factor (QF) used. The proposed approach leverages both the learning capacity of deep residual networks and prior knowledge of the JPEG compression pipeline. The proposed model operates in the YCbCr color space and performs JPEG artifact restoration in two phases using two different autoencoders: the first one restores the luma channel exploiting 2D convolutions; the second one, using the restored luma channel as a guide, restores the chroma channels explotining 3D convolutions.Extensive experimental results on three widely used benchmark datasets (i.e. LIVE1, BDS500, and CLASSIC-5) show that our model is able to outperform the state of the art with respect to all the evaluation metrics considered (i.e. PSNR, PSNR-B, and SSIM). This results is remarkable since the approaches in the state of the art use a different set of weights for each compression quality, while the proposed model uses the same weights for all of them, making it applicable to images in the wild where the QF used for compression is unkwnown. Furthermore, the proposed model shows a greater robustness than state-ofthe-art methods when applied to compression qualities not seen during training.

show abstract

“…Recently, it turns out that the same machinery can be used for pixel level operations, as well. For example, ConvNets have shown better performance than traditional methods for image restoration tasks such as deblocking [24] and restoration [25].…”

Section: B Convnet For Quality Enhancementmentioning

confidence: 99%

Convolutional Neural Network for Intermediate View Enhancement in Multiview Streaming

Tillo

Xiao

et al. 2018

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-Multiview video streaming continues to gain popularity due to the great viewing experience it offers, as well as its availability which has been enabled by increased network throughput and other recent technical developments. User demand for interactive multiview video streaming that provides seamless view switching upon request is also increasing. However, it is a highly challenging task to stream stable and high quality videos that allow real time scene navigation within the bandwidth constraint. In this paper a convolutional neural network (ConvNet) assisted seamless multiview video streaming system is proposed to tackle the challenge. The proposed method solves the problem from two perspectives: first, a ConvNet assisted multiview representation method is proposed, which provides flexible interactivity without compromising on multiview video compression efficiency. Second, a bit allocation mechanism guided by a navigation model is developed to provide seamless navigation and adapt to network bandwidth fluctuations at the same time. These two blocks work closely to provide an optimized viewing experience to users. They can be integrated into any existing multiview video streaming framework to enhance overall performance. Experimental results demonstrate the effectiveness of the proposed method for seamless multiview streaming.Index Terms-Multiview video streaming, Multiview navigation, Multiview video representation, Convolutional neural network.

show abstract

Adaptive non-local means filter for image deblocking

Cited by 61 publications

References 22 publications

Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC

Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC

Deep Residual Autoencoder for Blind Universal JPEG Restoration

Convolutional Neural Network for Intermediate View Enhancement in Multiview Streaming

Contact Info

Product

Resources

About