TY  - CONF
AU  - Saiping Zhang
AU  - Luis Herranz
AU  - Marta Mrak
AU  - Marc Gorriz Blanch
AU  - Shuai Wan
AU  - Fuzheng Yang
A2  - ICASSP
PY  - 2022//
TI  - DCNGAN: A Deformable Convolution-Based GAN with QP Adaptation for Perceptual Quality Enhancement of Compressed Video
BT  - 47th International Conference on Acoustics, Speech, and Signal Processing
N2  - In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical flows, deformable convolutions are more effective and efficient to align frames. Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos. Instead of aligning frames in a pairwise manner, the deformable convolution can process multiple frames simultaneously, which leads to lower computational complexity. Experimental results demonstrate that the proposed DCNGAN outperforms other state-of-the-art compressed video quality enhancement algorithms.
UR  - https://ieeexplore.ieee.org/document/9746702
L1  - http://refbase.cvc.uab.es/files/ZHM2022.pdf
UR  - http://dx.doi.org/10.1109/ICASSP43922.2022.9746702
N1  - MACO; 600.161; 601.379
ID  - Saiping Zhang2022
ER  -