SJTU Media Lab
SJTU Media Lab
News
People
Publications
Teaching
Resources
Jobs
Light
Dark
Automatic
"Image Reconstruction"
A Generative Compression Framework For Low Bandwidth Video Conference
Video conferences introduce a new scenario for video transmission, which focuses on keeping the fidelity of faces even in the low …
Dahu Feng
,
Yan Huang
,
Yiwei Zhang
,
Jun Ling
,
Anni Tang
,
Li Song
Cite
Code
DOI
TSGAN: A Two-Stream Generative Adversarial Network for Bit-Depth Expansion
The rapid development of display devices and the continuous improvement of visual quality requirements put urgent demands on high …
Zhen Yang
,
Li Song
,
Rong Xie
,
Wenjun Zhang
,
Lin Li
,
Yanan Feng
Cite
DOI
Learning-Based Quality Enhancement For Scalable Coded Video Over Packet Lossy Networks
The layered feature of scalable video coding (SVC) offers a sufficient adaptation to unreliable transmission. When network condition …
Shengwei Yu
,
Xun Tong
,
Yan Huang
,
Rong Xie
,
Li Song
Cite
DOI
Compression Priors Assisted Convolutional Neural Network for Fractional Interpolation
Fractional interpolation has been extensively utilized in a series of video coding standards to generate fractional precision …
Han Zhang
,
Li Song
,
Li Li
,
Zhu Li
,
Xiaokang Yang
Cite
DOI
CNN Based Post-Processing to Improve HEVC
Chen Li
,
Li Song
,
Rong Xie
,
Wenjun Zhang
Cite
DOI
Paralleling variable block size motion estimation of HEVC on CPU plus GPU platform
The emerging HEVC standard supports up to 12 variable block sizes ranging from 4×8/8×4 to 64×64 to conduct motion estimation (ME) and …
Xiangwen Wang
,
Li Song
,
Min Chen
,
Junjie Yang
Cite
DOI
Cite
×