1 code implementation • 16 Jun 2022 • Saiping Zhang, Luis Herranz, Marta Mrak, Marc Gorriz Blanch, Shuai Wan, Fuzheng Yang
In this paper we propose a generative adversarial network (GAN) framework to enhance the perceptual quality of compressed videos.
no code implementations • 13 May 2022 • Zhaocheng Liu, Luis Herranz, Fei Yang, Saiping Zhang, Shuai Wan, Marta Mrak, Marc Górriz Blanch
Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands.
no code implementations • 29 Jan 2022 • Xiao Huo, Dongyang Jin, Saiping Zhang, Fuzheng Yang
Specifically, the proposed method aligns two LFs captured by two hand-held LF cameras with a random relative pose, and extracts the corresponding row-aligned sub-aperture images (SAIs) to obtain an LF with a large baseline.
no code implementations • 22 Jan 2022 • Saiping Zhang, Luis Herranz, Marta Mrak, Marc Gorriz Blanch, Shuai Wan, Fuzheng Yang
Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos.
1 code implementation • 22 Sep 2021 • Saiping Zhang, Marta Mrak, Luis Herranz, Marc Górriz, Shuai Wan, Fuzheng Yang
In this paper, we introduce deep video compression with perceptual optimizations (DVC-P), which aims at increasing perceptual quality of decoded videos.
no code implementations • 11 Jan 2020 • Dongyang Jin, Saiping Zhang, Xiao Huo, Wei zhang, Fuzheng Yang
The proposed method is able to reuse traditional camera calibration methods for the direction parameter set.