Improve Video Quality Research Articles

Practically High Performant Neural Adaptive Video Streaming

Despite offering early promise, Deep Reinforcement Learning (DRL) suffers from several challenges in adaptive bitrate streaming stemming from the uncertainty and noise in network conditions. However, in this paper, we find that although these challenges complicate the training process, in practice, we can substantially mitigate their effects by addressing a key overlooked factor: the skewed input trace distribution in DRL training datasets. We introduce a generalized framework, Plume , to automatically identify and balance the skew using a three-stage process. First, we identify the critical features that determine the behavior of the traces. Second, we classify the traces into clusters. Finally, we prioritize the salient clusters to improve the overall performance of the controller. We implement our ideas with a novel ABR controller, Gelato , and evaluate the performance against state-of-the-art controllers in the real world for more than a year, streaming 59 stream-years of television to over 280,000 users on the live streaming platform Puffer. Gelato trained with Plume outperforms all baseline solutions and becomes the first controller on the platform to deliver statistically significant improvements in both video quality and stalling, decreasing stalls by as much as 75%.

FReD-ViQ: Fuzzy Reinforcement Learning Driven Adaptive Streaming Solution for Improved Video Quality of Experience

FReD-ViQ: Fuzzy Reinforcement Learning Driven Adaptive Streaming Solution for Improved Video Quality of Experience

Multi-Type Self-Attention-Based Convolutional-Neural-Network Post-Filtering for AV1 Codec

Over the past few years, there has been substantial interest and research activity surrounding the application of Convolutional Neural Networks (CNNs) for post-filtering in video coding. Most current research efforts have focused on using CNNs with various kernel sizes for post-filtering, primarily concentrating on High-Efficiency Video Coding/H.265 (HEVC) and Versatile Video Coding/H.266 (VVC). This narrow focus has limited the exploration and application of these techniques to other video coding standards such as AV1, developed by the Alliance for Open Media, which offers excellent compression efficiency, reducing bandwidth usage and improving video quality, making it highly attractive for modern streaming and media applications. This paper introduces a novel approach that extends beyond traditional CNN methods by integrating three different self-attention layers into the CNN framework. Applied to the AV1 codec, the proposed method significantly improves video quality by incorporating these distinct self-attention layers. This enhancement demonstrates the potential of self-attention mechanisms to revolutionize post-filtering techniques in video coding beyond the limitations of convolution-based methods. The experimental results show that the proposed network achieves an average BD-rate reduction of 10.40% for the Luma component and 19.22% and 16.52% for the Chroma components compared to the AV1 anchor. Visual quality assessments further validated the effectiveness of our approach, showcasing substantial artifact reduction and detail enhancement in videos.

Using GPU-Accelerated Pixel Format Conversions for Efficient Real-Time Video Streaming

Pixelweave Chromascale is a new open-source library that can leverage GPU computing to efficiently convert video frame pixel formats. The library enhances the computational performance of high-quality real-time video streaming by accelerating pre-frame conversions and offloading resource-intensive tasks from the CPU. It currently supports a wide range of pixel formats, including RGBA and chroma-subsampled YUV, using up to 16 bits per color channel. It is accessed through a C++ interface that triggers a GPU compute pipeline. It uses a novel approach that samples $2 \times 2$ pixel windows, ensuring the code is easily extensible and independent of source and destination formats. Evaluations of multiple video samples demonstrate significant improvement in frames-per-second when compared to existing state-of-the-art CPU-based libraries and show improved video quality in real-time streaming applications. Pixelweave technology has been integrated into a production tool to create numerous award-winning films, enabling more performant and color-accurate real-time streaming.

Video and image quality improvement using an enhanced optimized dehazing technique

Video and image quality improvement using an enhanced optimized dehazing technique

Nasal endoscopy: What have we been missing?

Despite the widespread adoption of nasal endoscopy (NE) in the evaluation of sinonasal disease, its diagnostic potential may still be underutilized. Developments in endoscopic technology have led to significant improvements in video quality and maneuverability. However, there is concern that NE continues to be used primarily for the identification of gross pathology, with relative neglect of more subtle findings such as surface features of inflammation and mucus. With fewer technical limitations to perceive these abnormalities, there is potential to greatly improve the diagnostic value of NE. The reader is herein asked to consider several important visual nuances encountered during NE, with the hope that this engenders an appreciation of the versatility of NE as a diagnostic tool.

Video Inpainting with Local and Global Refinement

Video inpainting is a crucial task in computer vision and video editing, involving in removing unnecessary objects and restoration of missing or corrupted regions within a video sequence. One approach that has gained prominence in recent years is the combination of local and global refinement techniques. This innovative strategy leverages the strengths of both local and global information to produce high-quality inpainted videos. In the context of video inpainting, local refinement focuses on accurately restoring missing or damaged regions by considering nearby pixels or frames. Encoder-decoder network can be employed to fill in gaps with content that seamlessly blends with the surrounding context. On the other hand, global refinement seeks to ensure temporal consistency and smooth transitions between frames, preventing noticeable artifacts or jittering in the inpainted video. In conclusion, by seamlessly blending local and global inpainting strategies, these methods can effectively remove unwanted elements from videos while preserving both spatial and temporal coherence. This technology finds applications in video editing, restoration of damaged archival footage, and even in the entertainment industry for special effects and scene corrections, ultimately contributing to the improvement of video quality and aesthetics. Keywords: Video Inpainting, Local and Global Refinement, Encoder-Decoder network, Recurrent Flow Completion, mask-guided sparse video Transformer, dual-domain propagation.

Complementary and Alternative Medicine for Hidradenitis Suppurativa Discussed on TikTok: A Cross-Sectional Analysis.

Hidradenitis suppurativa (HS) is a painful, chronic inflammatory skin disease that negatively affects patient quality of life, and conventional treatments are variably effective. As a result, patients often turn to complementary and alternative medicine (CAM) for pain relief. Social media enables HS patients to share treatment recommendations. TikTok is a popular social media platform, but little is known about the HS treatments discussed in TikTok videos.  Objective: To evaluate the content and quality of information on TikTok regarding CAM HS therapies.  Methods: A cross-sectional analysis was conducted by performing a search in TikTok using the terms #hidradenitissuppurativa, #hswarrior, #naturalremedy, #complementarymedicine, #alternativemedicine, and #HStreatment. Two independent reviewers evaluated video quality using the DISCERN and AVA instruments. Linear regressions compared the engagement, DISCERN, and AVA scores among different uploader types. In total, 91 TikTok videos were analyzed. Videos were uploaded by non-physicians (82.4), dermatologists (6.6%), and private companies (11.0%). The average DISCERN and AVA scores were 36.2 and 1.6, respectively (poor quality). Common CAM therapies were natural salves, turmeric, Epsom salts, elimination diets, and zinc supplements. Physician-uploaded videos were of significantly higher quality than videos by other uploader types, with an average DISCERN and AVA score of 44.3 (P<0.009) and 2.6 (P<0.001), respectively (fair quality). TikTok videos were poor quality (low DISCERN and AVA scores); physician-uploaded videos were fair quality. Dermatologists can improve video quality by adequately discussing the supporting evidence, mechanisms of action, and remaining questions for HS treatments.  J Drugs Dermatol. 2024;23(3):e93-96. doi:10.36849/JDD.7738e.

DMUST360: Distortion‐aware multicast‐unicast superposed transmission for multiuser 360‐degree video

Abstract360‐degree video has gained popularity since it is associated with immersive user experience of virtual reality content. However, providing high‐quality 360‐degree video for a large number of users is difficult, especially in limited bandwidth conditions. Nonorthogonal multiple access technology‐enabled multicast offers a possible solution, but it also introduces some challenges, including in terms of satisfying users' individual requirements, ensuring video quality and so forth. In order to address these issues, we introduce a novel distortion‐aware multicast‐unicast superposed transmission scheme for multiuser 360‐degree video, which combines the advantages of multicast, unicast, and nonorthogonal multiple access technologies with consideration of the field of view of multiple users. To improve video quality, a distortion minimization problem is formulated. Based on matching theory, we proposed a multicast‐unicast coalition game algorithm to solve the problem efficiently. A series of trace‐driven simulations are carried out, which have shown the effectiveness of the proposed solution in terms of video quality and throughput.

Video quality adaptation using CNN and RNN models for cost-effective and scalable video streaming Services

Video streaming services require adaptive bit rate strategies that optimize video quality based on network conditions and user preferences to provide a cost-effective and scalable solution. In this manuscript, we present a novel architecture that utilizes a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to extract features from the video stream and predict optimal bit rates for each frame. The CNN feature extractor extracts relevant features from the input video stream, which are then passed on to the RNN predictor, where the optimal bit rate is predicted to ensure a personalized viewing experience tailored to the current network conditions and specific user preferences. Our experimental results demonstrate that the proposed architecture achieves significant improvements in video quality while minimizing bandwidth usage and providing a better user experience. Specifically, our results show a 37.1% improvement in average bit rate, indicating that the proposed architecture optimizes the video quality and reduces bandwidth usage by 37.1% on average. We also observed a 16.6% improvement in Quality of Experience (QoE), meaning that users will perceive the video quality as better. Additionally, rebuffering was reduced by 87.5%, indicating that users enjoy smoother video playback without interruptions. Importantly, our architecture is optimized for Dynamic Adaptive Streaming over HTTP (DASH), addressing the need for efficient streaming over the most widely used protocol in the industry.

A novel method for video enhancement under low light using BFR-SEQT technique

ABSTRACT As typical frame rates allow limited exposure time, camera-captured videos under low-light conditions often suffer from poor contrast and noise. Existing models failed to consider dark and light areas' boundary pixels and varying low-illuminated night videos' weather conditions for removing noise and enhancing contrast. Hence, the video's visual appearance under low-light is improved using BFR-SEQT. Primarily, a video is inputted and converted into frames. Also, colour space is converted from which static and dynamic pixels are detected regarding frame differences. Using LoG-MF and KF algorithms, noise is removed from which foreground and background are separated using SD-FCM. Motion is estimated and features are extracted to enhance contrast. Then, pixel grouping using LC-GOA is done. Lastly, enhanced outputs from both phases are reconstructed and enhanced video is obtained. The proposed model improves video quality by enhancing contrast and removing noise with high PSNR values (27.6589db and 24.5478db), thus outperforming conventional methods.

ANALYSIS OF METHODS TO INCREASE QOE PARAMETERS FOR VIDEO STREAMING SERVICES

Video streaming services represent a new generation of television (DTV), which have become an integral part of modern digital culture. With the development of Internet technologies and the spread of broadband access, video streaming has become a popular and convenient way to consume multimedia content. Unlike traditional television, video streaming services provide the user with the ability to choose content, watch it at a convenient time and on different devices, which leads to new challenges and opportunities in improving the quality of user experience (QoE). One of the key elements that determine the quality of a video streaming service is the operator's transmission equipment and platform servers. These components provide content streaming over the Internet and affect such parameters as download speed, data stream stability and playback quality. Efficient management and optimization of the transmission equipment and servers can reduce latency, improve video quality and provide smoother streaming of content to end users. This research project aims to analyze methods for improving QoE parameters for video streaming services to better understand how technologies, algorithms and strategies can be applied to optimise the user experience in this new type of digital content. By considering factors such as video quality, adaptive streaming, traffic management, and many others, we aim to highlight key aspects that contribute to improving QoE and providing a more satisfactory user experience in video streaming services.

Cross-Attention and Seamless Replacement of Latent Prompts for High-Definition Image-Driven Video Editing

Recently, text-driven video editing has received increasing attention due to the surprising success of the text-to-image model in improving video quality. However, video editing based on the text prompt is facing huge challenges in achieving precise and controllable editing. Herein, we propose Latent prompt Image-driven Video Editing (LIVE) with a precise and controllable video editing function. The important innovation of LIVE is to utilize the latent codes from reference images as latent prompts to rapidly enrich visual details. The novel latent prompt mechanism endows two powerful capabilities for LIVE: one is a comprehensively interactive ability between video frame and latent prompt in the spatial and temporal dimensions, achieved by revisiting and enhancing cross-attention, and the other is the efficient expression ability of training continuous input videos and images within the diffusion space by fine-tuning various components such as latent prompts, textual embeddings, and LDM parameters. Therefore, LIVE can efficiently generate various edited videos with visual consistency by seamlessly replacing the objects in each frame with user-specified targets. The high-definition experimental results from real-world videos not only confirmed the effectiveness of LIVE but also demonstrated important potential application prospects of LIVE in image-driven video editing.

Robotic retroperitoneal para-aortic lymphadenectomy via single-site port

Para-aortic staging is sometimes a standard feature in the management of pelvic cancers. Minimal invasive approach is recommended. Several routes are possible: extra-peritoneal or intraperitoneal depending on the expertise of the surgeon. We performed several extraperitoneal para-aortic lymphadenectomy using the Da Vinci Xi robotic system through single-site incision. We have developed a step-by-step guide from patient installation, installation of the Gelpoint V monotrocar, docking of the robot arms, to surgery, with the aim of performing the most efficient and safest procedure.The surgery does not differ from standard laparoscopic extraperitoneal lymphadenectomy. The advantages of minimally invasive robotic surgery in this indication are comparable to those of the standard laparoscopy approach. But through single-site incision, the Da Vinci Xi robot improves video quality, plus its wristed tools facilitates movements compared to conventional laparoscopy.

Performance analysis of H2BR: HTTP/2-based segment upgrading to improve the QoE in HAS

HTTP Adaptive Streaming (HAS) plays a key role in over-the-top video streaming with the ability to reduce the video stall duration by adapting the quality of transmitted video segments to the network conditions. However, HAS still suffers from two problems. First, it incurs variations in video quality because of throughput fluctuation. Adaptive bitrate (ABR) algorithms at the HAS client usually select a low-quality segment when the throughput drops to avoid stall events, which impairs the Quality of Experience (QoE) of the end-users. Second, many ABR algorithms choose the lowest-quality segments at the beginning of a video streaming session to ramp up the playout buffer early on. Although this strategy decreases the startup time, clients can be annoyed as they have to watch a low-quality video initially. To address these issues, we introduced the H2BR technique (H TTP/2-B ased R etransmission) (Nguyen et al. 33) that utilizes certain features of HTTP/2 (including server push, multiplexing, stream priority, and stream termination) for late transmissions of higher-quality versions of video segments already in the client buffer, in order to improve video quality. Although H2BR was shown to enhance the QoE, limited streaming scenarios were considered resulting in a lack of general conclusions on H2BR’s performance. Thus, this article provides a profound evaluation to answer three open questions: (i) how H2BR’s performance is impacted by parameters at the server side (i.e., various encoding specifications), at the network side (i.e., packet loss rate), and at the client side (i.e., buffer size) on the performance of H2BR; (ii) how H2BR outperforms other state-of-the-art approaches in different configurations of the parameters above; (iii) how to effectively utilize H2BR on top of ABR algorithms in various streaming scenarios. The experimental results show that H2BR’s performance increases with the buffer size and decreases with increasing packet loss rates and/or video segment duration. The number of quality levels can negatively or positively impact on H2BR’s performance, depending on the ABR algorithm deployed. In general, H2BR is able to enhance the video quality by up to 17% and 14% in scalable video streaming and in non-scalable video streaming, respectively. Compared with an existing retransmission technique (i.e., SQUAD Wang et al., ACM Trans Multimed Comput Commun Applic (TOMM) 13(3s): 45, 49), H2BR shows better results with more than 10% in QoE and 9% in the average video quality.

Evaluation of the educational quality of publicly available online videos on laparoscopic jejunostomy by utilizing the LAP-VEGaS guidelines.

Despite its common nature, there is no data on the educational quality of publicly available laparoscopic jejunostomy training videos. The LAParoscopic surgery Video Educational GuidelineS (LAP-VEGaS) video assessment tool, released in 2020, has been developed to ensure that teaching videos are of appropriate quality. This study applies the LAP-VEGaS tool to currently available laparoscopic jejunostomy videos. A retrospective review of YouTube® videos was conducted for "laparoscopic jejunostomy." Included videos were rated by three independent investigators using LAP-VEGaS video assessment tool (0-18). Wilcoxon rank-sum test was used to evaluate differences in LAP-VEGaS scores between video categories and date of publication relative to 2020. Spearman's correlation test was performed to measure association between scores and length, number of views and likes. 27 unique videos met selection criteria. Academic and physician video walkthroughs did not demonstrate a significant difference in median scores (9.33 IQR 6.33, 14.33 vs. 7.67 IQR 4, 12.67, p = 0.3951). Videos published after 2020 demonstrated higher median scores than those published before 2020 (13 IQR 7.5, 14.67 vs. 5 IQR 3, 9.67, p = 0.0081). A majority of videos failed to provide patient position (52%), intraoperative findings (56%), operative time (63%), graphic aids (74%), and audio/written commentary (52%). A positive association was demonstrated between scores and number of likes (rs = 0.59, p = 0.0011) and video length (rs = 0.39, p = 0.0421), but not number of views (rs = 0.17, p = 0.3991). The majority of available YouTube® videos on laparoscopic jejunostomy fail to meet the basic educational needs of surgical trainees, and there is no difference between those produced by academic centers or independent physicians. However, there has been improvement in video quality following the release of the scoring tool. Standardization of laparoscopic jejunostomy training videos with the LAP-VEGaS score can ensure that videos are of appropriate educational value with logical structure.

Evaluating the Distribution, Quality, and Educational Value of Videos Related to Shoulder Instability Exercises on the Social Media Platform TikTok.

Because of the lack of scientific oversight, the quality, applicability, and consistency of healthcare-related TikTok videos have become a focus of research exploration. The orthopaedic surgery literature lags behind other medical fields in analyzing the widespread utilization of TikTok videos for medical information delivery. TikTok was queried using the hashtag #shoulderstabilityexercises, and 109 videos were included. The videos were collected by two authors and independently evaluated using DISCERN (a well-validated informational analysis tool) and shoulder stability exercise education score (a self-designed tool for the evaluation of shoulder instability-related exercises). DISCERN scores of videos uploaded by general users had significantly lower scores in all four categories than those uploaded by healthcare professionals (P < 0.001, P = 0.005, P = 0.002, and P < 0.001). For the shoulder stability exercise education score, general users had a significantly lower score than the healthcare professionals at 3.36 and 4.91 on a 25-point scale, respectively (P = 0.034). General users had more videos graded as very poor (84.2%) in comparison to the number of videos uploaded by healthcare professionals deemed very poor (51.5%). However, the remainder of healthcare professionals had their videos graded as poor (48.5%). Despite slightly improved video quality from healthcare professionals, the overall educational of the videos related to shoulder instability exercises was poor.

Adaptive and Efficient Hybrid In-loop Filter Based on Enhanced Generative Adversarial Networks with Sample Adaptive Offset Filter for HEVC/H-265

In this manuscript, an Adaptive and Efficient Hybrid In-loop Filter based on Enhanced Generative Adversarial Network Deblocking Filter (EGANDF) with Sample Adaptive Offset filter (EGANDF-SAO-HEVC) is proposed for High Efficiency Video Coding (HEVC)/H-265. In this, the proposed hybrid in-loop filter involves EGANDF and Sample Adaptive Offset (SAO) filter that lessens the blocking artifacts caused by block-wise processing for coding unit (CU), which is mainly used for improving the video quality. Initially, EGANDF is proposed for HEVC/H-265 for removing blocking artifacts along low computation. Here, the output of EGANDF is given to the SAO filter for reducing ringing artifacts by diminishing high-frequency components during quantization. Thus, the proposed method efficiently reduces artifacts for improving video quality performance. The proposed EGANDF-SAO-HEVC method is implemented in the working platform of HEVC reference software with MATLAB. Finally, the proposed EGANDF-SAO-HEVC model has attained 27.26%, 29.65%, 12.45% higher accuracy, 33.56%, 31.8%, 28.7% higher sensitivity, 34.7%, 33.5%, 32.6% higher specificity, 46.92%, 35.7%, 41.3% lower MSE, 25.7%, 29.7%, 35.6% higher PSNR, and 25.6%, 28.9%, 13.6% higher SSIM for using basketball video sequence when compared to the existing methods.

A fast sand-dust video quality improvement method using simple color balance and dynamic guided filtering

A fast sand-dust video quality improvement method using simple color balance and dynamic guided filtering

Application of Improved Image Processing Technology in New Media Short Video Quality Improvement in Film and Television Postproduction

With the development of film and television industry and the rise of new media short video, film and television postproduction process has higher and higher requirements for image quality. In film and television postproduction, optimizing the image quality can enhance the resolution and make the image more vivid and detailed. High-quality image can fully embody the value of film and television, as well as promote the development of new media short videos. This paper optimizes image quality by improving image processing technology, thus improving the quality and value of film and television and new media short videos. In this paper, a convolutional neural network combined with a nonlinear activation function is used to establish an improved image processing technology model to efficiently extract image features. This technology can enhance the ability to extract image features, improve the accuracy of image feature extraction, and then improve the image resolution and details, thus improving the image quality in the process of film and television postproduction. The results show that the average value of PSNR is 30.29. The average value of PSNR of the proposed algorithm is higher than that of other algorithms, indicating that the error between the image processed by the proposed algorithm and the original image is small. The average SSIM of the algorithm in this paper is 0.903, which is closer to 1. Compared with other algorithms, the structure processed by the algorithm in this paper is more similar to the original structure, resulting in a better graph. The algorithm in this paper has the best performance on both the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM). The improved image processing technology proposed in this paper can effectively improve the accuracy of image feature extraction, making film and television or new media short video images of higher quality.