Sorry, you need to enable JavaScript to visit this website.

Flow-Guided Temporal-Spatial Network for HEVC Compressed Video Quality Enhancement

Primary tabs

Citation Author(s):
Xiandong Meng, Xuan Deng, Shuyuan Zhu, Shuaicheng Liu and Bing Zeng
Submitted by:
XIANDONG MENG
Last updated:
31 March 2020 - 10:00pm
Document Type:
Poster
Document Year:
2020
Event:
Presenters Name:
Xiandong MENG
Paper Code:
DCC_141

Abstract 

Abstract: 

In this work, a flow-guided temporal-spatial network (FGTSN) is proposed to enhance the quality of HEVC compressed video. Specially, we first employ a motion estimation subnet via trainable optical flow module to estimate the motion flow between current frame and its adjacent frames. Guiding by the predicted motion flow, the adjacent frames are aligned to current frame. Then, a temporal encoder is designed to discover the variations between current frame and its warped frames. Finally, the reconstruction frame is generated by training the model in a multi-supervised fashion. Our method takes advantage of temporal-spatial information to enhance the compressed video Quality. Experimental results demonstrate the superior performance of our FGTSN method.

up
0 users have voted:

Dataset Files

DCC_M.pdf

(88)