SJTU Media Lab
SJTU Media Lab
News
People
Publications
Teaching
Resources
Jobs
Light
Dark
Automatic
"Visualization"
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
A Hybrid Model for Natural Face De-Identiation with Adjustable Privacy
As more and more personal photos are shared and tagged in social media, security and privacy protection are becoming an unprecedentedly …
Yunqian Wen
,
Bo Liu
,
Rong Xie
,
Yunhui Zhu
,
Jingyi Cao
,
Li Song
Cite
DOI
A VMAF Directed Perceptual Rate Distortion Optimization for Video Coding
Video Multimethod Assessment Fusion (VMAF), as a state-of-the-art learning-based objective assessment metric, has been demonstrated to …
Xun Tong
,
Chen Zhu
,
Rong Xie
,
Jian Xiong
,
Li Song
Cite
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
Weight-based bit allocation scheme for VR videos in HEVC
Since VR videos shown on the head-mounted display (HMD) is omnidirectional, the average distortion of VR videos in all directions shall …
BiJia Li
,
Li Song
,
Rong Xie
,
Wenjun Zhang
Cite
DOI
Video stabilization with L1–L2 optimization
Digital videos often suffer from undesirable camera jitters because of unstable camera motions. In this paper we present a novel video …
Hui Qu
,
Li Song
Cite
DOI
Cite
×