Organizing Co-chairs
  • Zhan Ma, Nanjing Univesity, China
  • Giuseppe Valenzise, CNRS, France
  • Dandan Ding, Hangzhou Normal University, China
  • Faranak Tohidi, Charles Sturt University, Australia
  • Pan Gao, Nanjing University of Aeronautics and Astronautics, China
  • Danillo Graziosi, Sony, US
Technical Program Commitee
  • Dong Tian, InterDigital, USA
  • Fernando Pereira, Instituto Superior Técnico, Portugal
  • Marco Carli, Roma Tre University, Italy
  • Patrick le Callet, University of Nantes, France
  • Simone Milani, University of Padova, Italy
  • Wei Hu, Peking University, China
  • Federica Battisti, University of Padova, Italy
  • Jean-Eudes Marvie, InterDigital, France
  • Lu Zhang, INSA Rennes, France
  • Zhu Li, University of Missouri-Kansas City, USA
  • Emin Zerman, Mid Sweden University, Sweden
  • Laura Toni,UCL,UK
  • Mylène Farias,University of Brasilia, Brasil
  • Mohammad Zavid Parvez,Australian Catholic University, Australia
  • Ashek Ahmmed, Charles Sturt University, Australia
  • Subrata Chakraborty,University of New England
  • Motiur Rahaman, Charles Sturt University, Australia
  • Hui Yuan, Shandong University, China
  • Wei Gao, Peking University, China
  • Zhengwei Wang, ByteDance AI Lab, China

The use of immersive media (e.g., point clouds, light fields, meshes, etc) enables mixing the physical and virtual world to create an unprecedented experience for applications like AR/VR (augmented/virtual reality), Digital Twin and the Metaverse. To make these applications feasible over current and future communication networks and maximize user experience, efficient compression of immersive media is essential. In addition to traditional rules-based compression methods explored in the past decades, in recent years deep learning has been applied to multimedia coding, yielding impressive coding gains in some cases. Furthermore, international standardization organizations like MPEG and JPEG are actively pushing the standardization of novel coding solutions for immersive content. Without doubt, this will be the future frontier for new media systems and services. However, technological barriers and challenges need to be overcome in developing the best solutions and standards.

This ICME workshop on Immersive Media Compression aims at bringing forward recent advances related to compression technologies for light fields, point clouds, meshes, etc. The goal is to gather researchers with diverse and interdisciplinary backgrounds to cover a variety of aspects related to compression (e.g., acquisition, processing, quality measurement, optimization, etc.), to efficiently develop Immersive Media Compression systems and technologies.

News

The slides of the keynote talks are now available!

  • The date of the workshop is confirmed to be July 10
  • Confirmed keynotes:
    • Dong Tian (InterDigital, US): "Learning Technologies for Immersive Media”
    • Stuart Perry (University of Technology of Sydney): "Learning-based Point Cloud Compression in JPEG"
  • We implement a fast track procedure for papers rejected by the ICME main conference and demonstrating an acceptable quality.
    • Authors will be requested to provide, in addition to the paper, a letter with responses to the reviewers’ comments.
    • Decision could be made by the chairs without additional reviews.
Program
Room: P1
8:30 – 8:35: WELCOME AND INTRODUCTION
8:35 – 9:20: KEYNOTE 1 – Dong Tian (InterDigital, US): "Learning Technologies for Immersive Media"
9:20 – 10:00: SESSION 1: 3D MESHES
9:20 – Texture coordinate prediction using structural information for MPEG V-DMC, Wenjie Zou, FuZheng Yang (Xidian University)
9:40 – DMVC: Deep Mesh Vertex Compression, Xinyao Zeng, Xudong Zhao, Linyao Gao, Yiling Xu, Yunfeng Guan (Shanghai Jiao Tong University)
10:00 – 10:30: Coffee break
10:30 – 11:50: SESSION 2: IMAGE-BASED FORMATS AND PROCESSING
10:30 – Disentangled Feature Distillation for Light Field Super-Resolution with Degradations, Linjie Zhou (Peking University), Wei Gao (SECE, Shenzhen Graduate School, Peking University), Ge Li (Peking University), Hui Yuan (School of Control Science and Engineering, Shandong University), Tiesong Zhao (Fuzhou University), Guanghui Yue (Shenzhen university)
10:50 – FBRA360: A Fuzzy-based bitrate adaptation scheme for 360° video streaming, Si-Ze Qian, Yuan Zhang, Tao Lin (Communication University of China)
11:10 – K3BO: Keypoint-Based Bounding Box Optimization for Radiance Field Reconstruction from Multi-View Images, Joshua Maraval, Nicolas RAMIN (b<>com), Lu Zhang (INSA Rennes)
11:30 – Learn how to prune pixels for multi-view neural image-based synthesis, Marta Milovanovic, Enzo Tartaglione (Télécom Paris - Institut Polytechnique de Paris), Marco Cagnazzo (University of Padova), Félix Henry (Orange Labs)
11:50 – 13:15: Lunch
13:15 – 14:00: KEYNOTE 2 – Stuart Perry (University of Technology of Sydney): "Learning-based Point Cloud Compression in JPEG"
14:00 – 15:00: SESSION 3: POINT CLOUDS
14:00 – Video-Based Point Cloud Compression Using Density-Based Variable Size Hexahedrons, Faranak Tohidi, Manoranjan Paul (Charles Sturt University, Australia)
14:20 – Normal-based Global Motion Estimation for LiDAR Point Cloud Lossless Geometry Compression, Wenhua Lou, Shuai, Lei Wei (Northwestern Polytechnical University), FuZheng Yang (Xidian University)
14:40 – Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation, Zihao Li, Pan Gao (Nanjing University of Aeronautics and Astronautics), Hui Yuan (School of Control Science and Engineering, Shandong University), Ran Wei (Science and Technology on Electro-optic Control Laboratory), Manoranjan Paul (Charles Sturt University, Australia)
Subject areas
  • Immersive video coding (omnidirectional, light fields, point clouds/meshes, etc.)
  • Immersive video processing and enhancement
  • Immersive multimedia (audio visual and multimodal)
  • Quality of Experience for Immersive multimedia
  • Streaming and networked solutions for Immersive multimedia
Important dates
  • Submission deadline: March 23 April 1;
  • Review submission deadline: April 18;
  • Author notification: April 24;
  • Camera-ready: May 1st;
Duration of the workshop: Full day
Paper Submission

Full-length papers of 6 pages in length reporting on original research are solicited. The reviewing is double blind and the paper submission link is: https://cmt3.research.microsoft.com/ICMEW2023. For detailed instructions, see http://2023.ieeeicme.org/.