MP2.L1: Emerging Trends in Learning-based Image and Video Compression - II
Mon, 28 Oct, 16:30 - 18:00 Gulf Standard Time (UTC +4)
Location: Capital Suite - 13
Session Type: Lecture
Session Co-Chairs: Giuseppe Valenzise, Université Paris-Saclay, CNRS, Centrale Supelec, France and Ivan Bajic, Simon Fraser University, Canada
Track: Special Sessions
Click the to view the manuscript on IEEE Xplore Open Preview
Mon, 28 Oct, 16:30 - 16:48 Gulf Standard Time (UTC +4)
 Special Session Paper

MP2.L1.1: A STUDY ON THE EFFECT OF COLOR SPACES IN LEARNED IMAGE COMPRESSION
Srivatsa Prativadibhayankaram, Mahadev Prasad Panda, Fraunhofer Institute for Integrated Circuits IIS, Germany; Jürgen Seiler, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany; Thomas Richter, Heiko Sparenberg, Siegfried Fößel, Fraunhofer Institute for Integrated Circuits IIS, Germany; André Kaup, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
Mon, 28 Oct, 16:48 - 17:06 Gulf Standard Time (UTC +4)
 Special Session Paper

MP2.L1.2: RES-NERV : RESIDUAL BLOCKS FOR A PRACTICAL IMPLICIT NEURAL VIDEO DECODER
Marwa Tarchouli, Thomas Guionnet, Marc Riviere, Ateme, France; Wassim Hamidouche, Meriem Outtas, Olivier Deforges, INSA Rennes, France
Mon, 28 Oct, 17:06 - 17:24 Gulf Standard Time (UTC +4)
 Best Paper Candidate

MP2.L1.3: Joint End-to-End Image Compression and Denoising: Leveraging Contrastive Learning and Multi-Scale Self-ONNs
Yuxin Xie, Li Yu, Nanjing University of Information Science and Technology, China; Farhad Pakdaman, Moncef Gabbouj, Tampere University, Finland
Mon, 28 Oct, 17:24 - 17:42 Gulf Standard Time (UTC +4)
 Special Session Paper

MP2.L1.4: Adaptive downsampling and spatial upconversion for point cloud compression
Yichen Zhou, Xinfeng Zhang, University of Chinese Academy of Sciences, China; Yingzhan Xu, Kai Zhang, Li Zhang, Bytedance Inc, China
Mon, 28 Oct, 17:42 - 18:00 Gulf Standard Time (UTC +4)
 Special Session Paper

MP2.L1.5: IMPROVING IMAGE CODING FOR MACHINES THROUGH OPTIMIZING ENCODER VIA AUXILIARY LOSS
Kei Iino, Shunsuke Akamatsu, Hiroshi Watanabe, Waseda University, Japan; Shohei Enomoto, Akira Sakamoto, Takeharu Eda, NTT Software Innovation Center, Japan