TP-V2.V7.11
STREAMING-CAPABLE HIGH-PERFORMANCE ARCHITECTURE OF LEARNED IMAGE COMPRESSION CODECS
Fangzheng Lin, Heming Sun, Jiro Katto, Waseda University, Japan
Session:
Lossy Coding of Images and Video
Track:
Image and Video Communications
Location:
Gather.Town 7
Presentation Time:
Tue, 4 Oct, 22:00 - 23:00 China Standard Time (UTC +8)
Tue, 4 Oct, 16:00 - 17:00 Central European Time (UTC +2)
Tue, 4 Oct, 14:00 - 15:00 UTC
Tue, 4 Oct, 10:00 - 11:00 Eastern Time (UTC -4)
Tue, 4 Oct, 16:00 - 17:00 Central European Time (UTC +2)
Tue, 4 Oct, 14:00 - 15:00 UTC
Tue, 4 Oct, 10:00 - 11:00 Eastern Time (UTC -4)
Session Co-Chairs:
Jean-Christophe Pesquet, CentraleSupélec and Andrea Cavallaro, Queen Mary University of London and Rebecca Willett, University of Chicago
Presentation
Discussion
Resources
No resources available.
Session TP-V2.V7
TP-V2.V7.1: LEARNING FREQUENCY-SPECIFIC QUANTIZATION SCALING IN VVC FOR STANDARD-COMPLIANT TASK-DRIVEN IMAGE CODING
Kristian Fischer, Fabian Brand, Christian Herglotz, André Kaup, Friedrich-Alexander-University Erlangen-Nürnberg, Germany
TP-V2.V7.2: OPTIMIZED LEARNED ENTROPY CODING PARAMETERS FOR PRACTICAL NEURAL-BASED IMAGE AND VIDEO COMPRESSION
Amir Said, Reza Pourreza, Hoang Le, Qualcomm Technologies, Inc., United States of America
TP-V2.V7.3: Deep Feature Compression Using Rate-Distortion Optimization Guided Autoencoder
Meguru Yamazaki, Yuichiro Kora, Takanori Nakao, Xuying Lei, Kaoru Yokoo, Fujitsu Limited, Japan
TP-V2.V7.4: P-FRAME CODING WITH GENERALIZED DIFFERENCE: A NOVEL CONDITIONAL CODING APPROACH
Fabian Brand, Jürgen Seiler, André Kaup, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
TP-V2.V7.5: AN EMPIRICAL APPROACH FOR OPTIMISING THE IMPACT OF A PREPROCESSOR IN A TRANSCODING PIPELINE
Varoun Hanooman, Anil Kokaram, Trinity College Dublin, Ireland; Yeping Su, Neil Birkbeck, Balu Adsumili, YouTube/Google, United States of America
TP-V2.V7.6: AN EFFICIENT SCHEME OF MULTI-HYPOTHESIS MOTION COMPENSATED PREDICTION FOR VIDEO CODING APPLICATIONS
Bohan Li, Jingning Han, Yaowu Xu, Google LLC, United States of America
TP-V2.V7.7: CONTENT-ADAPTIVE NEURAL NETWORK POST-PROCESSING FILTER WITH NNR-CODED WEIGHT-UPDATES
Maria Santamaria, Francesco Cricri, Jani Lainema, Ramin G. Youvalari, Honglei Zhang, Miska M. Hannuksela, Nokia Technologies, Finland
TP-V2.V7.8: GAUSSIAN DISTRIBUTION-BASED MODE SELECTION FOR INTRA PREDICTION OF SPATIAL SHVC
Dayong Wang, Xin Wang, Weisheng Li, Chongqing University of Posts and Telecommunications, China; Yu Sun, University of Central Arkansas, United States of America; Xin Lu, De Montfort University, United Kingdom of Great Britain and Northern Ireland; Frederic Dufaux, CNRSCentraleSupelec- Université Paris-Sud, France
TP-V2.V7.9: A HYBRID DEEP ANIMATION CODEC FOR LOW-BITRATE VIDEO CONFERENCING
Goluck Konuko, Universite Paris Saclay, France; Stéphane Lathuilière, Institut Polytechnique de Paris, France; Giuseppe Valenzise, Centre national de la recherche scientifique, France
TP-V2.V7.10: Non-separable Filtering with Side-Information and Contextually-Designed Filters for Next Generation Video Codecs
Onur Guleryuz, Debargha Mukherjee, Yue Chen, Keng-Shih Lu, Urvang Joshi, Google LLC, United States of America
TP-V2.V7.11: STREAMING-CAPABLE HIGH-PERFORMANCE ARCHITECTURE OF LEARNED IMAGE COMPRESSION CODECS
Fangzheng Lin, Heming Sun, Jiro Katto, Waseda University, Japan