Visual Perception Enhancement for HEVC Compressed Video Using a Generative Adversarial Network

Wang, Ting; He, Jingbo; Xiong, Shengwu; Karn, Pradeep; He, Xiaohai

doi:10.1109/ucet51115.2020.9205459

Cited by 7 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Huang et al [24] propose a novel network which filters the luminance channel separately from the pair of chrominance channels. Jin et al [25] and Wang et al [52] use a generative adversarial network to remove visual artifacts in compressed video. He et al [22] design a network that uses the partition information produced by the encoder to guide the quality enhancement process.…”

Section: Related Workmentioning

confidence: 99%

CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhancement

Zhao

Zheng

Yuan

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Constant bit rate (CBR) videos are widely used in streaming playback applications. However, the image quality of the CBR video is often unstable, especially for scenes with large motion. To this end, we design a new model to represent the distortion of High Efficiency Video Coding (HEVC) constant bit rate video, and propose a neural network for a constant bit rate video quality enhancement (CBREN). We propose a dual-domain restoration module (DRM) to jointly learn the prior knowledge in the pixel domain and the frequency domain. To address the degradation resulting from compression, we propose a twostep quantization degradation estimation strategy. The Inverse DCT (IDCT) Translation Unit (ITU) is used to constrain the quantization table of the constant bit rate video to a suitable range, and the Dynamic Alpha Unit (DAU) is used to finetune the quantization table according to the content of each frame. In order to effectively reduce the block distortion of different sizes produced in the compression process, we adopt a multi-scale network. Extensive experiments show that our approach can greatly enhance the quality of CBR compressed video. Moreover, our method can also be applied to constant quantization parameter (CQP) video enhancement tasks, and is certainly superior to existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhancement

Zhao

Zheng

Yuan

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…We compare the proposed DCNGAN with state-of-the-art video quality enhancement networks in [4] (MFQE 2.0), [5] (STDF), [9] (MW-GAN) 1 and [10] (VPE-GAN). LPIPS [17] and DISTS [18] are employed to quantitatively evaluate the perceptual quality of enhanced videos.…”

Section: Quantitative and Qualitative Comparisonmentioning

confidence: 99%

“…However, sometimes the objective quality is inconsistent with the perceptual quality [7]. To achieve higher quality of experience (QoE) [8], many works have aimed at enhancing the perceptual quality of compressed videos [9] [10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DCNGAN: A Deformable Convolutional-Based GAN with QP Adaptation for Perceptual Quality Enhancement of Compressed Video

Zhang¹,

Herranz²,

Mrak³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical flows, deformable convolutions are more effective and efficient to align frames. Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos. Instead of aligning frames in a pairwise manner, the deformable convolution can process multiple frames simultaneously, which leads to lower computational complexity. Experimental results demonstrate that the proposed DCNGAN outperforms other state-of-theart compressed video quality enhancement algorithms.

show abstract

“…The estimated location is used to warp the image reconstructed from the previous frame, and to produce an initial estimation of the current frame, in a manner similar to [26]. In [33], He et al uses an adversarial loss combined with L1 loss to enhance HEVC compressed videos. The first part of the loss lets the generator to add missing high frequency details, the second is the reconstruction term.…”

Section: Artifact Removal and Quality Restorationmentioning

confidence: 99%

Fast Video Visual Quality and Resolution Improvement using SR-UNet

Vaccaro

Bertini

Uricchio

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

Visual Perception Enhancement for HEVC Compressed Video Using a Generative Adversarial Network

Cited by 7 publications

References 13 publications

CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhancement

CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhancement

DCNGAN: A Deformable Convolutional-Based GAN with QP Adaptation for Perceptual Quality Enhancement of Compressed Video

Fast Video Visual Quality and Resolution Improvement using SR-UNet

Contact Info

Product

Resources

About