arXiv subjects

Marta Mrak

Publications and source records attributed to Marta Mrak.

25 records · Page 2Linked to original sources

arXiv2020

Analytic Simplification of Neural Network based Intra-Prediction Modes for Video Compression

With the increasing demand for video content at higher resolutions, it is evermore critical to find ways to limit the complexity of video encoding tasks in order to reduce costs, power consumption and environmental impact of video services. In the last few years, algorithms based on Neural Networks (NN) have been shown to benefit many conventional video coding modules. But while such techniques can considerably improve the compression efficiency, they usually are very computationally intensive. It is highly beneficial to simplify models learnt by NN so that meaningful insights can be exploited with the goal of deriving less complex solutions. This paper presents two ways to derive simplified intra-prediction from learnt models, and shows that these streamlined techniques can lead to efficient compression solutions.

eess.IV↗

arXiv2020

Estimation of Rate Control Parameters for Video Coding Using CNN

Rate-control is essential to ensure efficient video delivery. Typical rate-control algorithms rely on bit allocation strategies, to appropriately distribute bits among frames. As reference frames are essential for exploiting temporal redundancies, intra frames are usually assigned a larger portion of the available bits. In this paper, an accurate method to estimate number of bits and quality of intra frames is proposed, which can be used for bit allocation in a rate-control scheme. The algorithm is based on deep learning, where networks are trained using the original frames as inputs, while distortions and sizes of compressed frames after encoding are used as ground truths. Two approaches are proposed where either local or global distortions are predicted.

eess.IV↗

arXiv2019

End-to-End Conditional GAN-based Architectures for Image Colourisation

In this work recent advances in conditional adversarial networks are investigated to develop an end-to-end architecture based on Convolutional Neural Networks (CNNs) to directly map realistic colours to an input greyscale image. Observing that existing colourisation methods sometimes exhibit a lack of colourfulness, this paper proposes a method to improve colourisation results. In particular, the method uses Generative Adversarial Neural Networks (GANs) and focuses on improvement of training stability to enable better generalisation in large multi-class image datasets. Additionally, the integration of instance and batch normalisation layers in both generator and discriminator is introduced to the popular U-Net architecture, boosting the network capabilities to generalise the style changes of the content. The method has been tested using the ILSVRC 2012 dataset, achieving improved automatic colourisation results compared to other methods based on GANs.

eess.IV↗

arXiv2019

Fast Inter-Prediction based on Decision Trees for AV1 encoding

The AOMedia Video 1 (AV1) standard can achieve considerable compression efficiency thanks to the usage of many advanced tools and improvements, such as advanced inter-prediction modes. However, these come at the cost of high computational complexity of encoder, which may limit the benefits of the standard in practical applications. This paper shows that not all sequences benefit from using all such modes, which indicates that a number of encoder optimisations can be introduced to speed up AV1 encoding. A method based on decision trees is proposed to selectively decide whether to test all inter modes. Appropriate features are extracted and used to perform the decision for each block. Experimental results show that the proposed method can reduce the encoding time on average by 43.4\% with limited impact on the coding efficiency.

eess.IV↗

arXiv2019

Decision Trees for Complexity Reduction in Video Compression

This paper proposes a method for complexity reduction in practical video encoders using multiple decision tree classifiers. The method is demonstrated for the fast implementation of the 'High Efficiency Video Coding' (HEVC) standard, chosen because of its high bit rate reduction capability but large complexity overhead. Optimal partitioning of each video frame into coding units (CUs) is the main source of complexity as a vast number of combinations are tested. The decision tree models were trained to identify when the CU testing process, a time-consuming Lagrangian optimisation, can be skipped i.e a high probability that the CU can remain whole. A novel approach to finding the simplest and most effective decision tree model called 'manual pruning' is described. Implementing the skip criteria reduced the average encoding time by 42.1% for a Bjøntegaard Delta rate detriment of 0.7%, for 17 standard test sequences in a range of resolutions and quantisation parameters.

eess.IV↗

arXiv2019

A Benchmark of Visual Storytelling in Social Media

Media editors in the newsroom are constantly pressed to provide a "like-being there" coverage of live events. Social media provides a disorganised collection of images and videos that media professionals need to grasp before publishing their latest news updated. Automated news visual storyline editing with social media content can be very challenging, as it not only entails the task of finding the right content but also making sure that news content evolves coherently over time. To tackle these issues, this paper proposes a benchmark for assessing social media visual storylines. The SocialStories benchmark, comprised by total of 40 curated stories covering sports and cultural events, provides the experimental setup and introduces novel quantitative metrics to perform a rigorous evaluation of visual storytelling with social media data.

cs.MM↗

arXiv2018

Convolutional Neural Networks for Video Quality Assessment

Video Quality Assessment (VQA) is a very challenging task due to its highly subjective nature. Moreover, many factors influence VQA. Compression of video content, while necessary for minimising transmission and storage requirements, introduces distortions which can have detrimental effects on the perceived quality. Especially when dealing with modern video coding standards, it is extremely difficult to model the effects of compression due to the unpredictability of encoding on different content types. Moreover, transmission also introduces delays and other distortion types which affect the perceived quality. Therefore, it would be highly beneficial to accurately predict the perceived quality of video to be distributed over modern content distribution platforms, so that specific actions could be undertaken to maximise the Quality of Experience (QoE) of the users. Traditional VQA techniques based on feature extraction and modelling may not be sufficiently accurate. In this paper, a novel Deep Learning (DL) framework is introduced for effectively predicting VQA of video content delivery mechanisms based on end-to-end feature learning. The proposed framework is based on Convolutional Neural Networks, taking into account compression distortion as well as transmission delays. Training and evaluation of the proposed framework are performed on a user annotated VQA dataset specifically created to undertake this work. The experiments show that the proposed methods can lead to high accuracy of the quality estimation, showcasing the potential of using DL in complex VQA scenarios.

eess.IV↗