Residual-Based Post-Processing for HEVC

Ma, Li; Xing, Peiyin; Huang, Tiejun

doi:10.1109/mmul.2019.2922194

Cited by 12 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We list the average BD-rate results of our approach, DCAD [18], and Residual-VRN [20], [21] for RA, AI, LDP, and LDB configurations in Table 6. For each configuration, since DCAD and Residual-VRN are post-processing algorithms for luma pictures, the average BD-rate reduction on Y-PSNR of our approach is 4.55% more than DCAD and 2.37% more than Residual-VRN.…”

Section: Comparing With Other Methodsmentioning

confidence: 99%

“…Table 7 shows the BD-rate results of our approach and VDSR in [19] on cif sequences [26]. According to [19], we take the x265 platform as encoder, which is same as [20], [21] and DCAD [18] in the case of RA, AI, LDP and LDB for RA, AI, LDP and LDB configurantions. their approach.…”

Section: Comparing With Other Methodsmentioning

confidence: 99%

“…In this paper, the DCAD is claimed to have an average BD-rate reduction of 5.0%, 6.4%, 5.3% and 5.5% for AI, LDP, LDB, and RA configurations, respectively. L. Ma et al proposed a Residual-based Video Restoration Network (Residual-VRN) for video post-processing [20] [21]. Compared to HEVC baseline, their method performs better than DCAD with an average BD-rate reduction of 7.4%,9.4%,7.4% and 7.6% for AI, LDP, LDB, and RA configurations, respectively.…”

Section: B Cnn-based Post-processing Algorithms At the Decoder Endmentioning

confidence: 99%

“…2) the approaches improve video coding efficiency at the decoder end [18]- [21]. for some applications limited by the bandwidth and storage, the post-processing algorithms use the decoded videos as inputs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A CNN-Based Post-Processing Algorithm for Video Coding Efficiency Improvement

Zhao

Teng

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Lossy compression algorithms are widely used in video coding. However, lossy compressed videos exist some annoying distortion and artifacts, such as blocking, blurring, and ringing. Thus, coding efficiency improvement is a steady-state topic in the domain of video coding. High Efficiency Video Coding (HEVC), a recent video standard, adopts two in-loop filters for the improvement of the coding efficiency, including deblocking (DB) and sample adaptive offset (SAO). In a certain extent, traditional in-loop filters reduce the distortion and improve the video quality. But the reduction of the distortion is a nonlinear problem that is difficult to be solved by traditional linear filters. Recently, the progress of deep learning shows the possibility to settle the complex problems in the computer vision field. Meanwhile, according to the compressive sensing theory, the post-processing method at the decoder end can further enhance the coding efficiency. In this paper, we propose a variable-filter-size Residue-learning convolutional neural network with batch normalization layer (VRCNN-BN). Our model is an end-to-end model. We feed the decoded pictures to the model at the decoder end. Different from previous methods, we apply the model to luma pictures and chroma pictures, respectively. In order to comprehensively evaluate the coding performance of both luma and chroma components, the color-sensitivity-based combined PSNR (CS-PSNR) is exploited to measure the effectiveness of the proposed method. Compared to HEVC baseline, our approach achieves an average BD-rate reduction of 10.3%, 8.9%, 13.1% and 11.8% in terms of CS-PSNR for random access, all intra, low delay P and low delay B configurations, respectively. Abundant experimental results indicate that our method is better than existing similar methods. INDEX TERMS Convolutional neural network, end-to-end, post-processing, high efficiency video coding.

show abstract

Section: Comparing With Other Methodsmentioning

confidence: 99%

Section: Comparing With Other Methodsmentioning

confidence: 99%

Section: B Cnn-based Post-processing Algorithms At the Decoder Endmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A CNN-Based Post-Processing Algorithm for Video Coding Efficiency Improvement

Zhao

Teng

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…CNNs are now also playing an important role in image restoration (including super-resolution), and these approaches can also be employed for post-processing of compressed video content to improve the overall reconstruction quality. Although various researchers have implemented CNN-based post-processing approaches in the context of HEVC and VVC [8][9][10][11], most of these can only achieve coding gains for All Intra configurations, which offer lower coding efficiency compared to Random Access configurations based on hierarchical B frame structures. In addition, all the employed CNN models in these approaches were trained to optimize a simple loss function based on pixel distortions ( 1 or 2 loss), which can lead to over-smoothed reconstruction results.…”

Section: B Cnn-based Post Processingmentioning

confidence: 99%

Video Compression with CNN-based Post Processing

Zhang,

Ma,

Feng

et al. 2020

Preprint

View full text Add to dashboard Cite

In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content. Among various compression tools, post-processing can be applied on reconstructed video content to mitigate visible compression artefacts and to enhance overall perceptual quality. Inspired by advances in deep learning, we propose a new CNN-based post-processing approach, which has been integrated with two state-of-the-art coding standards, VVC and AV1. The results show consistent coding gains on all tested sequences at various spatial resolutions, with average bit rate savings of 4.0% and 5.8% against original VVC and AV1 respectively (based on the assessment of PSNR). This network has also been trained with perceptually inspired loss functions, which have further improved reconstruction quality based on perceptual quality assessment (VMAF), with average coding gains of 13.9% over VVC and 10.5% against AV1.

show abstract