BVI-DVC: A Training Database for Deep Video Compression

  title={BVI-DVC: A Training Database for Deep Video Compression},
  author={Di Ma and Fan Zhang and David R. Bull},
Deep learning methods are increasingly being applied in the optimisation of video compression algorithms and can achieve significantly enhanced coding gains, compared to conventional approaches. Such approaches often employ Convolutional Neural Networks (CNNs) which are trained on databases with relatively limited content coverage. In this paper, a new extensive and representative video database, BVI-DVC, is presented for training CNN-based video compression systems, with specific emphasis on… 
Video Compression With CNN-Based Postprocessing
A new convolutional neural network based postprocessing approach, which has been integrated with two state-of-the-art coding standards, versatile video coding (VVC) and AOMedia Video (AV1), which shows consistent coding gains on all tested sequences at various spatial resolutions.
Video compression with low complexity CNN-based spatial resolution adaptation
A novel framework is proposed which supports the flexible allocation of complexity between the encoder and decoder and employs a CNN model for video down-sampling at theEncoder and uses a Lanczos3 filter to reconstruct full resolution at the decoder.
Improved CNN-Based Learning of Interpolation Filters for Low-Complexity Inter Prediction in Video Coding
This paper introduces a novel explainable neural network-based inter-prediction scheme, to improve the interpolation of reference samples needed for fractional precision motion compensation.
Model Selection CNN-based VVC Quality Enhancement
A Convolutional Neural Network (CNN)-based post-processing algorithm for intra and inter frames of Versatile Video Coding (VVC) coded streams and an optional Model Selection (MS) strategy is adopted to pick the best trained model among available ones at the encoder side, and signal it to the decoder side.
A CNN-Based Prediction-Aware Quality Enhancement Framework for VVC
The main focus has been put on decisions defining the prediction signal in intra and inter frames, and to retain a low memory requirement for the proposed method, one model is used for all Quantization Parameters (QPs) with a Quantization Parameter (QP)-map, which is also shared between luma and chroma components.
Multi-Density Attention Network for Loop Filtering in Video Compression
A on-line scaling based multi-density attention network for loop filtering in video compression that outperforms the state-of-the-art methods and performs robustly on video content of different resolutions.
CVEGAN: A Perceptually-inspired GAN for Compressed Video Enhancement
The proposed CVEGAN generator benefits from the use of a novel Mul2Res block (with multiple levels of residual learning branches), an enhanced residual non-local block (ERNB) and an enhanced convolutional block attention module (ECBAM) to improve the representational capability.
VVC In-Loop Filtering Based on Deep Convolutional Neural Network
The VVC conventional in-loop filtering will be replaced by the suggested WSE-DCNN technique that is expected to eliminate the compression artifacts in order to improve visual quality, and numerical results demonstrate the efficacy of the proposed model.
MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering
A novel convolutional neural network architecture, MFRNet, for post-processing (PP) and in-loop filtering (ILF) in the context of video compression with significant and consistent coding gains over both anchor codecs and also over other existing CNN-based PP/ILF approaches based on Bjøntegaard Delta measurements.
Artificial intelligence in the creative industries: a review
It is concluded that, in the context of creative industries, maximum benefit from AI will be derived where its focus is human centric -- where it is designed to augment, rather than replace, human creativity.


Image and Video Compression With Neural Networks: A Review
The evolution and development of neural network-based compression methodologies are introduced for images and video respectively and the joint compression on semantic and visual information is tentatively explored to formulate high efficiency signal representation structure for both human vision and machine vision.
DVC: An End-To-End Deep Video Compression Framework
This paper proposes the first end-to-end video compression deep model that jointly optimizes all the components for video compression, and shows that the proposed approach can outperform the widely used video coding standard H.264 in terms of PSNR and be even on par with the latest standard MS-SSIM.
Convolutional Neural Network-Based Block Up-Sampling for HEVC
This paper introduces block-level down- and up-sampling into inter-frame coding with the help of CNN and implements the proposed scheme onto the high efficiency video coding (HEVC) reference software and performs a comprehensive set of experiments to evaluate the methods.
Gan-Based Effective Bit Depth Adaptation for Perceptual Video Compression
  • Di Ma, Fan Zhang, D. Bull
  • Computer Science
    2020 IEEE International Conference on Multimedia and Expo (ICME)
  • 2020
A convolutional neural networks (CNN) based EBD adaptation method is presented for perceptual video compression, in which the employed CNN models are trained using a generative adversarial network (GAN), with perception-based loss functions.
Perceptually-inspired super-resolution of compressed videos
A perceptually-inspired super-resolution approach (M-SRGAN) is proposed for spatial up-sampling of compressed video using a modified CNN model, which has been trained using a generative adversarial network (GAN) on compressed content with perceptual loss functions.
HEVC Intra Frame Coding Based on Convolutional Neural Network
An alternative intra frame coding framework based on convolutional neural network (CNN) is proposed in this paper and an early termination mechanism is proposed to further reduce the HEVC encoding complexity.
Enhanced Video Compression Based on Effective Bit Depth Adaptation
This paper presents a novel Convolutional Neural Network (CNN) based effective bit depth adaptation approach (EBDA-CNN) for video compression. It applies effective bit depth down-sampling before
Neural Inter-Frame Compression for Video Coding
This work presents an inter-frame compression approach for neural video coding that can seamlessly build up on different existing neural image codecs and proposes to compute residuals directly in latent space instead of in pixel space to reuse the same image compression network for both key frames and intermediate frames.
Deep Learning-Based Video Coding
In the hope of advocating the research of deep learning-based video coding, a case study of the developed prototype video codec, Deep Learning Video Coding (DLVC), which features two deep tools that are both based on convolutional neural network, namely CNN-based in-loop filter and CNN- based block adaptive resolution coding.
A CNN-Based Post-Processing Algorithm for Video Coding Efficiency Improvement
A variable-filter-size Residue-learning convolutional neural network with batch normalization layer (VRCNN-BN) with end-to-end model that is better than existing similar methods for coding efficiency improvement and comprehensively evaluates the coding performance of both luma and chroma components.