ERI: Generative Adversarial Networks for Video Coding

ERI：用于视频编码的生成对抗网络

• 批准号: 2138635
• 负责人: Ying Liu
• 金额: $ 19.62万
• 依托单位: Santa Clara University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-02-01 至 2025-01-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2138635&HistoricalAwards=false
• 关键词: ERI; Generative; Adversarial; Networks; Video

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).Video coding is an important technology that compresses video signals to save transmission bandwidth and to provide Internet users with visually pleasing decoded videos. Inspired by recent breakthroughs in deep learning, convolutional neural networks have been increasingly exploited into video coding algorithms to provide significant coding gains compared to conventional approaches. Nevertheless, existing convolutional neural network-based video coding schemes tend to generate blurry decoded images which are inconsistent with human perception, and the high computational complexity of these schemes hinders their deployment on power-constrained and computation resource-limited devices, such as smart phones and tablets. Recently, the generative adversarial network demonstrated its capability of decoding sharp and photo-realistic images at low bit rates, but little research has investigated its potential for video compression. This project will develop generative adversarial network-based video coding systems to enhance the coding efficiency, meanwhile providing decoded videos with high perceptual quality. The project will also investigate low-complexity algorithms to reduce the power consumption and to accelerate the inference speed of the proposed video coding systems so that they are suitable for mobile and low-latency applications. The success of the project is expected to accelerate the economic growth of streaming video services to benefit people’s daily professional and entertainment activities. It will advance surveillance video services to enhance public safety in places such as airport, offices, highway, and road intersections. The research activities of the project will provide opportunities to train graduate and undergraduate students including minority and under-represented groups through theses research, senior design projects, as well as machine learning and artificial intelligence courses. The research results of the project will be showcased in a summer engineering seminar program to motivate high school students to pursue science and engineering majors in college.This project will address two problems: (1) How to leverage temporal correlations among video frames and explore scene dynamics in a generative adversarial network-based video coding architecture? Two approaches are proposed: a hierarchical predictive coding approach, and a spatial-temporal coding architecture based on 3-dimensional convolution. Since most existing generative adversarial network models are for still image compression, the success of this research will open the door to generative adversarial network-based coding systems for video coding professionals. (2) How to reduce the computational complexity of deep video coding networks? Despite the performance benefits of deep learning-based video coding tools, few of them are currently being adopted in real-world scenarios. This is due to the high computational complexity, slow inference speed and the large graphic processing unit memory requirements associated with deep network computation. To address this problem, the proposed research will develop algorithms to reduce the complexity, model size and model parameters of deep learning-based video coding models via separable convolution operations. The research results will accelerate the deployment of deep video coding models in real-world applications.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该奖项是根据2021年《美国救援计划法》的全部或部分资助（公共法律117-2）。VIDEO编码是一项重要技术，可压缩视频信号以节省传输带宽并为互联网用户提供视觉上令人满意的解码视频。受深度学习的最新突破的启发，卷积神经网络已越来越多地探索到视频编码算法中，与传统方法相比，可以提供显着的编码收益。然而，现有的基于卷积神经网络的视频编码方案倾向于产生模糊的解码图像，这些图像与人类的感知不一致，并且这些方案的高计算复杂性阻碍了它们在功率受限和计算资源限制的设备上的部署，例如智能手机和平板电脑。最近，通用的对抗网络证明了其以低比特率以低比率解码锋利和照片现实图像的能力，但是很少的研究研究了其视频压缩的潜力。该项目将开发一般的基于网络的视频编码系统，以提高编码效率，同时提供具有高感知质量的解码视频。该项目还将研究低复杂性算法，以减少功耗并加速提议的视频编码系统的推理速度，以便它们适合移动和低延迟应用程序。预计该项目的成功将加速流媒体视频服务的经济增长，从而使人们的日常专业和娱乐活动受益。它将推进监视视频服务，以增强机场，办公室，高速公路和道路交叉路口等地方的公共安全。该项目的研究活动将通过这些研究，高级设计项目以及机器学习和人工智能课程来培训培训毕业生和本科生，包括少数民族和代表性不足的团体。该项目的研究结果将在夏季工程开创性计划中展示，以激励高中生在大学中攻读科学和工程专业的专业。该项目将解决两个问题：（1）如何利用视频框架之间的临时相关性并探索基于通用的对手网络基于网络的视频编码体系结构中的场景动态？提出了两种方法：一种层次预测编码方法，以及基于三维卷积的时空编码结构。由于大多数现有的通用对抗网络模型都是用于静止图像压缩的，因此这项研究的成功将为视频编码专业人员的基于对抗性网络的通用网络编码系统打开大门。 （2）如何降低深视频编码网络的计算复杂性？尽管基于深度学习的视频编码工具具有性能好处，但在现实世界中，其中很少有人被采用。这是由于高计算复杂性，缓慢的推理速度和与深网计算相关的大图形处理单元内存需求。为了解决这个问题，拟议的研究将开发算法，以通过单独的卷积操作来减少基于深度学习的视频编码模型的复杂性，模型大小和模型参数。研究结果将加速现实世界应用中深层视频编码模型的部署。该奖项反映了NSF的法定任务，并通过使用基金会的知识分子优点和更广泛的影响审查标准来评估诚实地通过评估来诚实地支持。

项目成果

A generative adversarial network for video compression

• DOI: 10.1117/12.2618714
• 发表时间: 2022-05
• 作者: Pengli Du;Ying Liu;Nam Ling;Lingzhi Liu;Yongxiong Ren;M. Hsu

Learned image compression with transformers

• DOI: 10.1117/12.2656516
• 发表时间: 2023-06
• 作者: Tianma Shen;Y. Liu

Side Information Driven Image Coding for Machines

• DOI: 10.1109/pcs56426.2022.10018039
• 发表时间: 2022-12
• 期刊: 2022 Picture Coding Symposium (PCS)
• 作者: Zhongpeng Zhang;Y. Liu

Generative Video Compression with a Transformer-Based Discriminator

• DOI: 10.1109/pcs56426.2022.10018030
• 发表时间: 2022-12
• 期刊: 2022 Picture Coding Symposium (PCS)
• 作者: Pengli Du;Y. Liu;Nam Ling;Yongxiong Ren;Lingzhi Liu

A Survey of Efficient Deep Learning Models for Moving Object Segmentation

用于运动物体分割的高效深度学习模型综述

• DOI: 10.1561/116.00000140
• 发表时间: 2023
• 期刊: APSIPA Transactions on Signal and Information Processing
• 影响因子: 3.2
• 作者: Hou, Bingxin;Liu, Ying;Ling, Nam;Ren, Yongxiong;Liu, Lingzhi
• 通讯作者: Liu, Lingzhi