MP2.L302.5
DEEP CNN-BASED PRE-ENCODING PERCEPTUAL QUALITY CONTROL AND PREDICTION
Maryam Jenab, Shahram Shirani, McMaster university, Canada
Session:
MP2.L302: Perceptual Image Processing Lecture
Track:
Applications of Machine Learning
Location:
Room 302
Presentation Time:
Mon, 9 Oct, 17:42 - 18:00 Malaysia Time (UTC +8)
Session Chair:
Aladine Chetouani, Université d'Orléans
Session MP2.L302
MP2.L302.1: LEARNED IMAGE COMPRESSION GUIDED ADAPTIVE QUANTIZATION FOR PERCEPTUAL QUALITY
Cheng Chen, Google Inc., United States of America; Ruiqi Geng, University of Wisconsin-Madison, United States of America; Bohan Li, Maryla Ustarroz-Calonge, Frank Galligan, Jingning Han, Yaowu Xu, Google Inc., United States of America
MP2.L302.2: CONTOUR-ASSISTED LONG-RANGE PERCEPTUAL NETWORK FOR CAMOUFLAGED INSTANCE SEGMENTATION
JunJie Cui, FengMing Sun, Xia Yuan, Nanjing University of Science and Technology, China
MP2.L302.3: LEARNT DEEP HYPERPARAMETER SELECTION IN ADVERSARIAL TRAINING FOR COMPRESSED VIDEO ENHANCEMENT WITH A PERCEPTUAL CRITIC
Darren Ramsook, Anil Kokaram, Trinity College Dublin, Ireland
MP2.L302.4: DYNAMIC RANGE TRANSFORMER (DRT): LEARNING ENHANCED LOG-PERCEPTUAL INFORMATION WITH SWIN-FOURIER CONVOLUTION NETWORK FOR HDR IMAGING
Heunseung Lim, Joongchol Shin, Jinsol Choi, Joonki Paik, Chung-Ang University, Korea, Republic of
MP2.L302.5: DEEP CNN-BASED PRE-ENCODING PERCEPTUAL QUALITY CONTROL AND PREDICTION
Maryam Jenab, Shahram Shirani, McMaster university, Canada
Contacts