Marta Mrak

Marta Mrak

Auto-generated profile, based on publicly available information

Marta Mrak

University of London , London , UK

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2019
Verified
Conference Paper
Open access
NWNatasha Westland
Natasha Westland
ADAndre Seixas Dias
Andre Seixas Dias
MMMarta Mrak
Marta Mrak
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.

5 June 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
CZChengyi Zou
Chengyi Zou
SWShuai Wan
Shuai Wan
TJTiannan Ji
Tiannan Ji
MBMarc Gorriz Blanch
Marc Gorriz Blanch
MMMarta Mrak
Marta Mrak
LHLuis Herranz
Luis Herranz
Neural networks can be successfully used for cross-component prediction in video coding. In particular, attention-based architectures are suitable for chroma intra prediction using luma information because of their capability to model relations between different channels. However, the complexity of such methods is still very high and should be further reduced, especially for decoding. In this paper, a cost-effective attention-based neural network is designed for chroma intra prediction. Moreover, with the goal of further improving coding performance, a novel approach is introduced to utilize more boundary information effectively. In addition to improving prediction, a simplification methodology is also proposed to reduce inference complexity by simplifying convolutions. The proposed schemes are integrated into H.266/Versatile Video Coding (VVC) pipeline, and only one additional binary block-level syntax flag is introduced to indicate whether a given block makes use of the proposed method. Experimental results demonstrate that the proposed scheme achieves up to -0.46%/-2.29%/-2.17% BD-rate reduction on Y/Cb/Cr components, respectively, compared with H.266/VVC anchor. Reductions in the encoding and decoding complexity of up to 22% and 61%, respectively, are achieved by the proposed scheme with respect to the previous attention-based chroma intra prediction method while maintaining coding performance.

14 December 2020 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
MBMarc Gorriz Blanch
Marc Gorriz Blanch
SBSaverio Giovanni Blasi
Saverio Giovanni Blasi
ASAlan Smeaton
Alan Smeaton
NONoel O'Connor
Noel O'Connor
MMMarta Mrak
Marta Mrak
Neural networks can be successfully used to improve several modules of advanced video coding schemes. In particular, compression of colour components was shown to greatly benefit from usage of machine learning models, thanks to the design of appropriate attention-based architectures that allow the prediction to exploit specific samples in the reference region. However, such architectures tend to be complex and computationally intense, and may be difficult to deploy in a practical video coding pipeline. This work focuses on reducing the complexity of such methodologies, to design a set of simplified and cost-effective attention-based architectures for chroma intra-prediction. A novel size-agnostic multi-model approach is proposed to reduce the complexity of the inference process. The resulting simplified architecture is still capable of outperforming state-of-the-art methods. Moreover, a collection of simplifications is presented in this paper, to further reduce the complexity overhead of the proposed prediction architecture. Thanks to these simplifications, a reduction in the number of parameters of around 90% is achieved with respect to the original attention-based methodologies. Simplifications include a framework for reducing the overhead of the convolutional operations, a simplified cross-component processing model integrated into the original architecture, and a methodology to perform integer-precision approximations with the aim to obtain fast and hardware-aware implementations. The proposed schemes are integrated into the Versatile Video Coding (VVC) prediction pipeline, retaining compression efficiency of state-of-the-art chroma intra-prediction methods based on neural networks, while offering different directions for significantly reducing coding complexity.

9 May 2024 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
CZChengyi Zou
Chengyi Zou
SWShuai Wan
Shuai Wan
MBMarc Gorriz Blanch
Marc Gorriz Blanch
LMLuka Murn
Luka Murn
MMMarta Mrak
Marta Mrak
LHLuis Herranz
Luis Herranz
Exemplar-based colorization aims to generate plausible colors for a grayscale image with the guidance of a color reference image. The main challenging problem is finding the correct semantic correspondence between the target image and the reference image. However, the colors of the object and background are often confused in the existing methods. Besides, these methods usually use simple encoder-decoder architectures or pyramid structures to extract features and lack appropriate fusion mechanisms, which results in the loss of high-frequency information or high complexity. To address these problems, this paper proposes a lightweight semantic attention-guided Laplacian pyramid network (SAGLP-Net) for deep exemplar-based colorization, exploiting the inherent multi-scale properties of color representations. They are exploited through a Laplacian pyramid, and semantic information is introduced as high-level guidance to align the object and background information. Specially, a semantic guided non-local attention fusion module is designed to exploit the long-range dependency and fuse the local and global features. Moreover, a Laplacian pyramid fusion module based on criss-cross attention is proposed to fuse high frequency components in the large-scale domain. An unsupervised multi-scale multi-loss training strategy is further introduced for network training, which combines pixel loss, color histogram loss, total variance regularisation, and adversarial loss. Experimental results demonstrate that our colorization method achieves better subjective and objective performance with lower complexity than the state-of-the-art methods.


1 January 2006
Verified
Conference Paper
Open access
PDF file
NSNikola Sprljan
Nikola Sprljan
MMMarta Mrak
Marta Mrak
EIEbroul Izquierdo
Ebroul Izquierdo