AI-based Image and Video Coding

Wei Gao is an Assistant Professor at the School of Electronic and Computer Engineering, Peking University, Shenzhen, China. He earned his Ph.D. in Computer Science from the City University of Hong Kong in February 2017. Dr. Gao's research focuses on multimedia coding, multimedia processing, and multimodal learning, areas directly relevant to the topics explored in this book.With over 160 high-quality technical papers published, Dr. Gao has contributed significantly to multimedia coding standardization, submitting more than 50 technical proposals. He is the author or co-author of two influential books, and is an elected member of the IEEE Visual Signal Processing and Communications Technical Committee (VSPC-TC), and APSIPA Image Video and Multimedia Technical Committee (IVM-TC). He serves on the editorial board of Elsevier Signal Processing, and has organized workshops at prominent conferences such as IEEE ICME and ACM MM.In addition to his academic achievements, Dr. Gao leads several open-source projects, including OpenAICoding, OpenPointCloud, and OpenDatasets, providing valuable resources for the research community. As a Senior Member of IEEE, he is also a frequent speaker at international conferences, where he shares his expertise on deep learning and multimedia technologies.

• .- Chapter 1 Introduction to Image and Video Coding.- 1.1 Basic Concept of Image and Video Data.- 1.2 Representative Image and Video Datasets.- 1.3 AI-based Compression Requirement for Image and Video.- 1.4 Image and Video Coding Performance Evaluation.- 1.5 Organization of This Book.- 1.6 Summary.- Chapter 2 Fundamentals for Deep Learning-based Image and Video Coding.- 2.1 Introduction.- 2.2 Fundamental Knowledge of Deep Learning.- 2.3 Autoencoder and Variational Autoencoder.- 2.4 Principles and Framework of Deep Learning-based Image and Video Coding.- 2.5 Summary.- Chapter 3 Image and Video Quality Assessment and Perception Models.- 3.1 Introduction.- 3.2 Quality Assessment of Image and Video.- 3.3 Just Noticeable Distortion of Image and Video.- 3.4 Visual Attention Modeling of Image and Video.- 3.5 Comparative Analysis.- 3.6 Summary.- Chapter 4 Deep Learning-based Image Coding.- 4.1 Introduction.- 4.2 Representative Methods of Lossless Image Coding.- 4.3 Representative Methods of Lossy Image Coding.- 4.4 Comparative Analysis.- 4.5 Summary.- Chapter 5 Deep Learning-based Video Coding.- 5.1 Introduction.- 5.2 Framework and Key Components.- 5.3 Representative Methods of Video Coding.- 5.4 Comparative Analysis.- 5.5 Summary.- Chapter 6 Deep Learning-based 3D and Multimodal Coding.- 6.1 Introduction.- 6.2 Overall Framework and Datasets.- 6.3 Representative Methods of 3D and Multimodal Coding.- 6.4 Comparative Analysis.- 6.5 Summary.- Chapter 7 Human and Machine Vision-Oriented Image and Video Coding.- 7.1 Introduction.- 7.2 Representative Methods of Human Perception-based Coding.- 7.3 Representative Methods of Machine Perception-based Coding.- 7.4 Comparative Analysis.- 7.5 Summary.- Chapter 8 Compression Artifacts Removal for Image and Video Coding.- 8.1 Introduction.- 8.2 Representative Methods of Compressed Image Artifacts Reduction.- 8.3 Representative Methods of Compressed Video Artifacts Reduction.- 8.4 Comparative Analysis.- 8.5 Summary.- Chapter 9 Deep Learning-based Image and Video Coding Standards.- 9.1 Introduction.- 9.2 Overview of International Standards.- 9.3 IEEE AI-based Image and Video Coding Standard.- 9.4 JPEG AI-based Image and Video Coding Standard.- 9.5 MPEG Video Coding for Machines Standard.- 9.6 MPAI End-to-End Video Coding Standard.- 9.7 Comparative Analysis.- 9.8 Summary.- Chapter 10 Implementations for Deep Learning-based Image and Video Coding.- 10.1 Introduction.- 10.2 Basics of Neural Network Compression.- 10.3 Software and Hardware Platforms for Acceleration.- 10.4 Lightweight Methods for Deep Compression Network.- 10.5 Comparative Analysis.- 10.6 Summary.- Chapter 11 Open Source Projects for Deep Learning-based Image and Video Coding.- 11.1 Introduction.- 11.2 Representative Open Source Projects for Image Coding.- 11.3 Representative Open Source Projects for Video Coding.- 11.4 Comparative Analysis.- 11.5 Summary.- Chapter 12 Future Works for AI-based Image and Video Coding.- 12.1 Future Work on Quality Assessment and Perception Models for Image and Video.- 12.2 Future Work on Deep Learning-based for Image Coding.- 12.3 Future Work on Deep Learning-based for Video Coding.- 12.4 Future Work on Deep Learning-based for 3D and Multimodal Coding.- 12.5 Future Work on Human and Machine Vision Oriented Image and Video Coding.- 12.6 Future Work on Compression Artifacts Removal for Image and Video Coding.- 12.7 Future Work on Deep Learning-based Image and Video Coding Standards.- 12.8 Future Work on Implementations for Deep Learning-based Image and Video Coding.- 12.9 Future Work on Open Source Projects for Deep Learning-based Image and Video Coding.