Proceedings ArticleDOI
AI Gets Creative
Marta Mrak
- pp 1-2
Reads0
Chats0
TLDR
Looking forward, this penetration of AI opens new challenges, such as interpretability of deep learning (to enable use AI in an accountable way as well as to enable AI-inspired low-complexity algorithms) and applicability in systems which require low- complexity solutions and/or do not have enough training data.Abstract:
Numerous breakthroughs in multimedia signal processing are being enabled thanks to applications of machine learning in tasks such as multimedia creation, enhancement, classification and compression [1]. Notably, in the context of production and distribution of television programmes, it has been successfully demonstrated how Artificial Intelligence (AI) can support innovation in the creative sector. In the context of delivering TV programmes of stunning visual quality, the applications of deep learning have enabled significant advances when the original content is of poor quality / resolution, or when delivery channels are very limited. Examples when the enhancement of originally poor quality is needed include new content forms (e.g. user generated content) and historical content (e.g. archives), while limitations of delivery channels can, first of all, be addressed by improving content compression. As a state-of-the-art example, the benefits of deep-learning solutions have been recently demonstrated within an end-to-end platform for management of user generated content [2], where deep learning is applied to increase video resolution, evaluate video quality and enrich the video by providing automatic metadata. Within this particular application space where large amount of user generated content is available, the progress has also been made in addressing visual story editing using social media data in automatic ways, making programmes from large amount of content faster [3]. Broadcasters are also interested in restauration of historical content more cheaply. For example, adding colour to "black and white" content has until now been an expensive and time-consuming task. However, recently new algorithms have been developed to perform the task more efficiently. Generative Adversarial Networks (GANs) have become the baseline for many image-to-image translation tasks, including image colourisation. Aiming at the generation of more naturally coloured images from "black and white" sources, newest algorithms are capable of generalisation of the colour of natural images, producing realistic and plausible results [4]. In the context of content delivery, new generations of compression standards enable significant reduction of required bandwidth [5], however, with a cost of increased computational complexity. This is another area where AI can be utilised for better efficiency - either in its simple forms as decision trees [6,7] or more advanced deep convolutional neural networks [8]. Looking forward, this penetration of AI opens new challenges, such as interpretability of deep learning (to enable use AI in an accountable way as well as to enable AI-inspired low-complexity algorithms) and applicability in systems which require low-complexity solutions and/or do not have enough training data. However, overall further benefits of these new approaches include automatization of many traditional production tasks which has the potential to transform the way content providers make their programmes in cheaper and more effective ways.read more
Citations
More filters
Posted Content
Towards Transparent Application of Machine Learning in Video Processing.
TL;DR: This work introduces principles for simplification of learned models targeting improved transparency in implementing machine learning for video production and distribution applications, showing how bitrate savings and reduced complexity can be achieved by simplifying relevant deep learning models.
Book ChapterDOI
Scene-Adaptive Temporal Stabilisation for Video Colourisation Using Deep Video Priors
TL;DR: In this article , a generalised framework for colourisation of complex videos with an optimised few-shot training strategy was proposed to learn scene-aware video priors. But the proposed architecture is jointly trained to stabilise the input video and to cluster its frames with the aim of learning scene-specific modes.
References
More filters
Proceedings ArticleDOI
End-to-End Conditional GAN-based Architectures for Image Colourisation
TL;DR: In this paper, an end-to-end architecture based on Convolutional Neural Networks (CNNs) is proposed to directly map realistic colors to an input greyscale image.
Proceedings ArticleDOI
Decision Trees for Complexity Reduction in Video Compression
TL;DR: A novel approach to finding the simplest and most effective decision tree model called ‘manual pruning’ is described, and implementing the skip criteria reduced the average encoding time by 42.1% for a Bjøntegaard Delta rate detriment.
Proceedings ArticleDOI
Estimation of Rate Control Parameters for Video Coding Using CNN
TL;DR: In this article, 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, where networks are trained using the original frames as inputs, while distortions and sizes of compressed frames after encoding are used as ground truths.
Posted Content
Decision Trees for Complexity Reduction in Video Compression
TL;DR: In this paper, a method for complexity reduction in practical video encoders using multiple decision tree classifiers is proposed, which 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.
Proceedings ArticleDOI
Fast Inter-prediction Based on Decision Trees for AV1 Encoding
TL;DR: In this article, a method based on decision trees is proposed to selectively decide whether to test all inter-prediction modes, which can reduce the encoding time on average by 43.4%.