Deep learning techniques in video coding and quality analysis

Topiwala, Pankaj; Krishnan, Madhu; Dai, Wei

doi:10.1117/12.2322025

Cited by 8 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A ML-based coding unit (CU) depth decision method for High Efficiency Video. Deep learning is explored for video coding quality analysis [3]. Coding efficiency is enhanced using a Squeezeand-Excitation Filtering CNN (SEFCNN) structure [10].…”

Section: ░ 2 Related Researchmentioning

confidence: 99%

“…Conventional techniques often fail to capture the complex spatial and temporal interactions in video data, leading to suboptimal compression and quality loss [2]. This necessitates innovative solutions that align with developing network capabilities and user expectations for high-quality, low-latency video [3]. STreamNet, a proposed framework, addresses this by combining Temporal Convolutional Networks (TCNs) and Bi-directional Long Short-Term Memory (BiLSTM) for precise spatial-temporal fusion, fast coding, optimized interframe prediction, and accurate future frame prediction.…”

Section: ░ 1 Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Video Coding Framework with Spatial-Temporal Fusion for Optimized Streaming in Next-Generation Networks

Charles,

Khan,

Rao

2023

IJEER

View full text Add to dashboard Cite

Predicting future frames and improving inter-frame prediction are ongoing challenges in the field of video streaming. By creating a novel framework called STreamNet (Spatial-Temporal Video Coding), fusing bidirectional long short-term memory with temporal convolutional networks, this work aims to address the issue at hand. The development of STreamNet, which combines spatial hierarchies with local and global temporal dependencies in a seamless manner, along with sophisticated preprocessing, attention mechanisms, residual learning, and effective compression techniques, is the main contribution. Significantly, STreamNet claims to provide improved video coding quality and efficiency, making it suitable for next-generation networks. STreamNet has the potential to provide reliable and optimal streaming in high-demand network environments, as shown by preliminary tests that show a performance advantage over existing methods.

show abstract

Section: ░ 2 Related Researchmentioning

confidence: 99%

Section: ░ 1 Introductionmentioning

confidence: 99%

Adaptive Video Coding Framework with Spatial-Temporal Fusion for Optimized Streaming in Next-Generation Networks

Charles,

Khan,

Rao

2023

IJEER

View full text Add to dashboard Cite

show abstract

“…Second, VQA can be used in receiver video restoration (restore for best visual quality). This could be combined with deep learning to train blocks of video frames on the original video, which can provide effective restoration in compressed and other distorted videos [3], [6], [7]. This is a large and powerful application, especially when done offline; but it is not the focus of this paper.…”

Section: Review Of Vqas and Their Usesmentioning

confidence: 99%

VMAF and variants: towards a unified VQA

Topiwala

Dai

Pian

et al. 2021

Applications of Digital Image Processing XLIV

Self Cite

View full text Add to dashboard Cite

Video quality assessment (VQA) is now a fastgrowing subject, beginning to mature in the full reference (FR) case, while the burgeoning no reference (NR) case remains challenging. We investigate variants of the popular VMAF video quality assessment algorithm for the FR case, using support vector regression and feedforward neural networks, and extend it to the NR case, using the same learning architectures, to develop a partially unified framework for VQA. When heavily trained, algorithms such as VMAF perform well on test datasets, with 90%+ match; but predicting performance in the wild is better done by training/testing from scratch, as we do. Even from scratch, we achieve 90%+ performance in FR, with gains over VMAF. And we greatly reduce complexity vs. leading recent NR algorithms, VIDEVAL, RAPIQUE, yet exceed 80% in SRCC. In our preliminary testing, we find the improvements in trainability, while also constraining computational complexity, as quite encouraging, suggesting further study and analysis.

show abstract