Variational deep image restoration

JW Soh, NI Cho - IEEE Transactions on Image Processing, 2022 - ieeexplore.ieee.org
This paper presents a new variational inference framework for image restoration and a
convolutional neural network (CNN) structure that can solve the restoration problems …

Efficient in-loop filtering based on enhanced deep convolutional neural networks for HEVC

Z Pan, X Yi, Y Zhang, B Jeon… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
The raw video data can be compressed much by the latest video coding standard, high
efficiency video coding (HEVC). However, the block-based hybrid coding used in HEVC will …

A stable variant of linex loss SVM for handling noise with reduced hyperparameters

S Shrivastava, S Shukla, N Khare - Information Sciences, 2023 - Elsevier
Abstract Support Vector Machine (SVM) primarily uses the hinge loss function with maximum
margin. The boundary instances determine the separating hyperplanes. However, in real …

Extended openmax approach for the classification of radar images with a rejection option

AH Oveis, E Giusti, S Ghio… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The closed-set assumption in conventional classifiers, such as the Softmax, constrains deep
networks to select an output from the given known classes. However, the classification in a …

Attention-based dual-scale CNN in-loop filter for versatile video coding

MZ Wang, S Wan, H Gong, MY Ma - IEEE Access, 2019 - ieeexplore.ieee.org
As the upcoming video coding standard, Versatile Video Coding (ie, VVC) achieves up to
30% Bjøntegaard delta bit-rate (BD-rate) reduction compared with High Efficiency Video …

AGARNet: Adaptively gated JPEG compression artifacts removal network for a wide range quality factor

Y Kim, JW Soh, NI Cho - IEEE Access, 2020 - ieeexplore.ieee.org
Most of existing compression artifacts reduction methods focused on the application for low-
quality images and usually assumed a known compression quality factor. However, images …

QA-Filter: A QP-adaptive convolutional neural network filter for video coding

C Liu, H Sun, J Katto, X Zeng… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Convolutional neural network (CNN)-based filters have achieved great success in video
coding. However, in most previous works, individual models were needed for each …

A global appearance and local coding distortion based fusion framework for CNN based filtering in video coding

J Yue, Y Gao, S Li, H Yuan… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In-loop filtering is used in video coding to process the reconstructed frame in order to
remove blocking artifacts. With the development of convolutional neural networks (CNNs) …

Review and evaluation of end-to-end video compression with deep-learning

HM Yasin, SY Ameen - … of Modern Trends in Information and …, 2021 - ieeexplore.ieee.org
Recent years have shown exponential growth in video processing and transfer through the
Internet and other applications. With the restriction on bandwidth, processing, and storage …

MO-QoE: Video QoE using multi-feature fusion based optimized learning models

M Ghosh, C Singhal - Signal Processing: Image Communication, 2022 - Elsevier
The escalating demand for video content and streaming services has made it a predominant
medium of exchanging information in the modern era. Videos are processed, compressed …