TU5.L4.2
SEMANTICS-GUIDED GENERATIVE IMAGE COMPRESSION
Cheng-Lin Wu, Simon Fraser University, Canada; Hyomin Choi, InterDigital, United States; Ivan Bajic, Simon Fraser University, Canada
Session:
TU5.L4: Image and Video Communications 2 Lecture
Track:
[IV-COM] Image and video communications
Location:
Room 2
Presentation Time:
Tue, 16 Sep, 16:45 - 17:00 Anchorage Time (UTC -8)
Session Chair:
Giuseppe Valenzise, CNRS L2S, University Paris-Saclay, France
Presentation
Discussion
Resources
No resources available.
Session TU5.L4
TU5.L4.1: RATE-DISTORTION OPTIMIZATION WITH NON-REFERENCE METRICS FOR UGC COMPRESSION
Samuel Fernandez-Menduiña, Xin Xiong, Eduardo Pavez, Antonio Ortega, University of Southern California, United States; Neil Birkbeck, Balu Adsumilli, Google Inc., United States
TU5.L4.2: SEMANTICS-GUIDED GENERATIVE IMAGE COMPRESSION
Cheng-Lin Wu, Simon Fraser University, Canada; Hyomin Choi, InterDigital, United States; Ivan Bajic, Simon Fraser University, Canada
TU5.L4.3: LEARNED HYBRID VIDEO CODING FOR HUMAN PERCEPTION AND MULTIPLE MACHINE VISION TASKS
Martin Benjak, Saifullah Khan, Leibniz Universität Hannover, Germany; Yi-Hsin Chen, Wen-Hsiao Peng, National Yang Ming Chiao Tung University, Taiwan; Jörn Ostermann, Leibniz Universität Hannover, Germany
TU5.L4.4: Error correction for DNA-based image storage
Davi Lazzarotto, Michela Testolina, Touradj Ebrahimi, École Polytechnique Fédérale de Lausanne, Switzerland
TU5.L4.5: WEIGHTED AVERAGE PREDICTION FOR REGION ADAPTIVE HIERARCHICAL TRANSFORM IN SOLID GEOMETRY POINT CLOUD COMPRESSION
Yingzhan Xu, Kai Zhang, Li Zhang, Bytedance Inc., China
TU5.L4.6: Generative Face Video Compression Using Depth Estimation and Compressed Sensing
Hao Chang, Cheolkon Jung, Xidian University, China
Contacts