A weekly survey of the best in the field of audio and video technology.
News submission: mailto:contribute@livevideost… .
Tip: link jump only support public related links
HDR: A visual feast for users
With the development of The Times, people are more and more not satisfied with the limited color of the screen picture, and begin to study how to make the picture more similar to the real world. In this LivevideOstackCON 2021 Shanghai station conference, we invited Zhang Jiajie from the Audio and Video Technology Department of Kuaishou. He starts with a few short stories to analyze why photos don’t perfectly reproduce the real world, and shares the dry stuff about HDR high dynamic range video.
OneVPL with FFMPEG /GStreamer hardware codec
People are less familiar with the use of hardware Codec than software Codec. In this LivevideOstackCon 2021 Shanghai conference, we invited Intel media engineer — Xu Guangxin to share Intel’s latest development progress in hardware codec for us.
IETF Interview: HTTP/3 Global share continues to grow, and the outlook for QUIC is bright
This article is IETF’s recent interview with Lucas Pardue on QUIC standardization. Grant Gross, IETF Blog.
Merge and split HTTP requests in detail
This article presents a simple experiment that attempts to analyze the data for merging and splitting in HTTP and whether concurrent requests affect other requests.
VVC fast affine motion compensation
VVC uses multi-type tree (MTT) for block partitioning, which provides a more flexible way of block partitioning, but also greatly increases the complexity. On this basis affine motion compensation (AME) increases the complexity. In this paper, features are extracted to effectively reflect the statistical characteristics of MTT and AME, and the AME process with redundant features is used to save the time of AME processing.
An overview of University of Science and Technology of China AI image/video codec
This paper, from the University of Science and Technology of China team, reviews representative work on image/video codec using deep learning.
https://zhuanlan.zhihu.com/p/…
WeChat small game live – Android cross process rendering push stream practice
WeChat small for performance and safety, and a series of game, run in a separate process, in the environment will not initialize video broadcast related modules, that means little game of audio and video data must be across processes is transmitted to the main process flow, brought a series of challenges to us achieve little game live.
Cisco WebEx and Next Generation Video Conferencing
Videoconferencing has become increasingly used in People’s Daily lives, especially in the wake of the COVID-19 epidemic, which has led to the rapid growth of the videoconferencing market, leading to the continuous updating of Cisco’s network video technology. In this session, we invited Thomas Davies, Chief Engineer of Cisco’s Collaboration Technologies Group, to share with us the development history of AV1, the challenges of developing AV1, and the future of AV2 and its role in real-time communication.
VideoLab – High performance and flexible iOS video editing and effects framework
VideoLab is an open source, high-performance and flexible iOS video editing and effects framework that provides a more Adobe After Effect approach. The core of the framework is based on AVFoundation and Metal.
Principle and implementation of audio and video synchronization
This article mainly describes the audio and video synchronization principle, and common audio and video synchronization scheme, and with the code example, to show how to take the audio playback time as the benchmark, the video is synchronized to the audio in order to achieve video and audio synchronous playback.
AlicloudVoice Enhancement Algorithm: Enable real-time conference systems to enter the era of ultra-clear sound quality
In recent years, with the development of real-time communication technology, online meeting gradually become people indispensable important office tools in the work, according to incomplete statistics, about 75% for pure online meeting audio conference, which don’t need to open the camera and screen sharing function, voice quality and clarity of this meeting is important experience for the online meeting.
Facebook’s new effort: Hubert for self-supervised representation learning for speech recognition, generation, and compression
To open the door to modeling these types of rich lexical and nonlexical information in audio, Facebook has introduced Hubert, a new method for learning self-supervised phonetic representations. Hubert matches or even surpasses SOTA in speech recognition, speech generation and speech compression.
Video quality evaluation: challenges and opportunities
This article is edited from the speech delivered by Wang Haiqiang, assistant researcher of Pengcheng Laboratory, on LivevideoStack online sharing. Based on his own practical experience, he explained the challenges and opportunities of video quality evaluation in detail.
Evaluate video using the advanced video quality tool AVQT
This article is based on the topic of Evaluate Videos with the Advanced Video Quality Tool shared by Pranav Sodhani at WWDC 2021. Pranav Sodhani, from Apple’s display and color technology team, has expertise in algorithm development, machine learning, color science, and video technology.
The world’s first open source image recognition system is online!
When it comes to image recognition believe that everyone has been very familiar with, this technology already deeply into every aspect of our life, small to face unlock, pay, punching, hotel, driving violations identified within the camera, online star with the graph SouTu, big to automatically in driving a car driving auxiliary, auxiliary diagnosis of medical imaging, Image and video analysis, editing, re-creation, etc…
Two yuan new gameplay! Generate different styles of little sister animation images, skin color, hair style are variable
An input face image, it can generate a variety of style of animation image. Researchers at the University of Illinois at Urbana-Champaign have done just that, with a novel GaN transfer method that achieves a one-to-many generation effect.
How far has target detection come? | CVHub take you talk about the development of the target detection this 22 years
The field of target detection has been developed for more than 20 years. From the early traditional methods to the current deep learning methods, the accuracy is getting higher and the speed is getting faster, which is due to the continuous development of deep learning and other related technologies. This article will make a systematic introduction to the development of target detection field, aiming to build a complete knowledge architecture for readers, as well as understand the technology stack related to target detection and its future development trend.
[](https://mp.weixin.qq.com/s?__…
Half-Life: Alex Developers: How hard is it to develop VR hand interactions?
Japanese gaming site Kotaku recently caught up with Half-Life: Alix hand interaction developer Kerry Davis to find out what other directions were explored while developing the game, and which ones were hard for the player to detect, while also optimizing the details of the experience.
[](https://mp.weixin.qq.com/s?__…
The success of self-driving cars depends on teleoperation
Teleoperation technology is a kind of technical means to achieve the remote interaction between human and the controlled object. The control end of teleoperation is local, and its execution end is somewhere in remote space that cannot be directly perceived locally. The technology is now used mostly in robots. Teleoperation is usually just remote operation. Teleoperation is also a promising technology for self-driving cars. Because at the moment, it seems that for at least the next 10 to 20 years, autonomous driving will not be completely humanized. It will still require human intervention. The management of nuclear power plants or the pilot of aircraft in the world today is all human intervention, rather than 100 percent artificial intelligence control.
CVPR | 2021 tesla pure visual automated driving the latest progress
At the CVPR 2021 Autopilot Workshop, Andrej Karpathy, Director of Tesla AI, spoke about the latest developments in Tesla’s pure vision, including Autopilot and FSD.
Activity recommended
Buy before July 4 and get 20% off. Click here or scan the QR code for more details.
Illustration from __Pexels