SJTU Media Lab
SJTU Media Lab
News
People
Publications
Teaching
Resources
Jobs
Light
Dark
Automatic
"Decoding"
Realistic Talking Face Synthesis With Geometry-Aware Feature Transformation
Recent studies have shown remarkable success in synthesizing realistic talking faces by exploiting generative adversarial networks. …
Han Xue
,
Jun Ling
,
Li Song
,
Rong Xie
,
Wenjun Zhang
Cite
DOI
Deep Video Inverse Tone Mapping
Inverse tone mapping is an important topic in High Dynamic Range technology. Recent years, deep learning based image inverse tone …
Yucheng Xu
,
Li Song
,
Rong Xie
,
Wenjun Zhang
Cite
DOI
Rate control model for high dynamic range video
This paper describes a luminance based rate control (RC) model for high dynamic range (HDR) video. A novel mathematical relationship …
Lixun Bai
,
Li Song
,
Rong Xie
,
Liang Zhang
,
Zhengyi Luo
Cite
DOI
Machine learning based VP9-to-HEVC video transcoding
As more and more coding standards are developed for videos with higher resolution and higher frame rates, the conversion between them …
Xiangyu Li
,
Rong Xie
,
Li Song
,
Liang Zhang
Cite
DOI
Optimized nested protection for video Region of Interest with Raptor codes
Due to the best effort feature of many existing transmission channels, video streams often suffer from inevitable transmission errors. …
Zhengyi Luo
,
Li Song
,
Shibao Zheng
,
Nam Ling
Cite
DOI
Analysis and comparison of FEC and FEC-ARQ protection schemes based on RS and Raptor code
Four protection schemes based on RS and Raptor code as well as FEC and hybrid FEC-ARQ are analyzed and compared for erasure channels in …
Pei Wang
,
Li Song
,
Songyu Yu
,
Libo Yang
Cite
DOI
Cite
×