Agenda

Plenary presentation (Chair: Ivan Bajic, Simon Fraser University)       
14:00 – 15:00 Perception and Quality of Immersive Media,
Aljosa Smolic (Trinity College Dublin)

Session 1 (Chair: Søren Forchhammer, Technical University of Denmark)
15:00 – 15:12 A Generative Compression Framework for Low Bandwidth Video Conference
Dahu Feng (Shanghai Jiao Tong University); Yan Huang (Shanghai Jiao Tong University); Yiwei Zhang (Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University); Jun Ling (Shanghai Jiao Tong University); Anni Tang (Shanghai JiaoTong University); Li Song (Shanghai Jiao Tong University)
15:12 – 15:24 Enhancing Quality of Experience for the Cloud Virtual Reality Gaming: An Object-aware Video Encoding
Wenjie Zou (Xidian University); Shixuan Feng (Xidian University); Xionghui Mao (Xidian University); FuZheng Yang (Xidian University); Zhibin Ma (Huawei Technologies Co., Ltd.,)
15:24 – 15:36 Multi-View Image Feature Correlation Guided Cost Aggregation for Multi-View Stereo
Yawen Lai (Peking University); Ke Qiu (Peking University); Ronggang Wang (Peking University)
15:36 – 15:48 Real-time Unsupervised Multi-view Depth Estimation Network for Virtual View Synthesis
Ke Qiu (Peking University); Song Gu (Peking University); Shiyi Liu (Peking University); Yawen Lai (Peking University); Yangang Cai (Peking University); Ronggang Wang (Peking University)
15:48 – 16:00 Attention Based Facial Expression Manipulation
Feng Wang (Shanghai Jiao Tong University); Yuzhuo Fu (sjtu); Suncheng Xiang (Shanghai Jiao Tong University); Ting Liu (Shanghai Jiao Tong University)

Session 2 (Chair: Homer Chen, National Taiwan University)
16:00 – 16:12 Multiscale Deep Context Modeling for Lossless Point Cloud Geometry Compression
Dat Thanh NGUYEN (L2S, CNRS, CentraleSupelec); Maurice Quach (L2S, CNRS, CentraleSupelec); Giuseppe Valenzise (CNRS); Pierre Duhamel (CNRS)
16:12 – 16:24 Deep Learning-Based Blind Quality Assessment of 3D Point Clouds
Aladine Chetouani (Université d'Orléans, France); Maurice Quach (L2S, CNRS, CentraleSupelec); Giuseppe Valenzise (CNRS); Frederic Dufaux (CNRS)
16:24 – 16:36 Real-Time Adaptive Switching Mechanism Towards Viewport-Adaptive Omnidirectional Video Streaming Mingyi Yang (State Key Laboratory of ISN, Xidian University, Xi’an, China); Hong Liang (State Key Laboratory of ISN, Xidian University, Xi’an, China); FuZheng Yang (Xidian University)
16:36 – 16:48 Visual Saliency Prediction on 360 Degree Images With CNN
Xinlang Chen (Nanjing University of Aeronautics and Astronautics); Pan Gao (Nanjing University of Aeronautics and Astronautics); Ran Wei (Science and Technology on Electro-optic Control Laboratory)
16:48 – 17:00 Multi-Generator Adversarial Networks for Light Field Saliency Detection
Hongyan Cai (Hefei University of Technology); Xudong Zhang (Hefei University of Technology); Rui Sun (Hefei University of Technology); Ronald Poppe (Utrecht University); Jun Zhang (Hefei University of Technology)
17:00 – 17:12 A Spatio-Angular Filter for High Quality Sparse Light Field Refocusing
Martin Alain (Trinity College Dublin); Aljosa Smolic (Trinity College Dublin, Ireland)

Panel (Chair: Frédéric Dufaux, CNRS)
17:15 – 18:00 Panel on Hyper-Realistic Multimedia for Enhanced Quality of Experience
Panelists:
Marta Mrak, BBC R&D, UK
Dong Tian, InterDigital, USA
Rafal Mantiuk, University of Cambridge, UK
Jiaying Liu, Peking University, China

Contact Person: Frédéric Dufaux
https://www.realvision-itn.eu/Events/ICME-2021-Workshop-Agenda
20 SEPTEMBER 2021