Original article was published on Deep Learning on Medium
Reading: Multi-Scale CNN — Deep Network-Based Frame Extrapolation (HEVC Inter Prediction)
5.3% and 2.8% BD-Rate Reduction Under LDP & LDB configurations
In this story, “Deep Network-Based Frame Extrapolation With Reference Frame Alignment” (Multi-Scale CNN), by University of Science and Technology of China, and Peking University, is presented. I just call it “Multi-Scale CNN” since they mentioned “our multi-scale CNN …” in the passage. In this paper:
- Reference frames are aligned.
- The aligned frames are used to extrapolated by a trained deep network. With alignment, training difficulty is reduced and accuracy is improved.
This is a paper in 2020 TCSVT where TCSVT has a high impact factor of 4.046. (Sik-Ho Tsang @ Medium)