Decoder-side HEVC quality enhancement with scalable convolutional neural network

By Ren Yang, Mai Xu, Zulin Wang. 2017

120 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Trevor Darrell
3. Dacheng Tao
4. Jitendra Malik
5. Xiaogang Wang
6. Li Fei-Fei
7. Ming-Hsuan Yang
8. Andrew Zisserman

In Signal Processing

1. Mai Xu
2. Zulin Wang
3. Ren Yang
4. Tianyi Li
5. Xiaodan Song
6. Oren Rippel
7. Lubomir D. Bourdev
8. Steve Branson

Citations in the corpus

• Learned Video Compression (2018, background): “These include improved motion compensation and interpolation [54, 21, 58, 31], intra-prediction coding [40], post-processing refinement [7, 55, 26, 56, 48, 57, 41, 17], and rate control [28].”
• Multi-frame Quality Enhancement for Compressed Video (2018, methodology): “More importantly, the video encoder does not need to be modified when applying the DCAD [34] and DSCNN [38] approaches.”
• A Practical Convolutional Neural Network as Loop Filter for Intra Frame (2018, background): “Recent research has investigated the deep learning approach, especially convolutional neural network (CNN), on post-processing [3, 4, 5, 6] or loop filtering [7, 8].”
• Enhancing Quality for HEVC Compressed Videos (2017, methodology): “The QE-CNN model is advanced by adopting Parametric Rectified Linear Unit (PReLU) and residual learning, to achieve better quality performance than [18] for both I and P/B frames.”