HEVC 9

[논문 리뷰] Video Compression based on Jointly Learned Down-Sampling and Super-Resolution Networks

오늘 살펴 볼 논문은 2021년 VCIP에서 발표된 논문으로, 제목은 'Video Compression based on Jointly Learned Down-Sampling and Super-Resolution Networks' [1] 이다. down-sampling과 super-resolution 기반의 video coding 논문이며 앞서 리뷰한 논문인 'RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling-Based Video Coding' [2] 를 비교 논문으로 하여 실험 결과를 낸 바가 있어 리뷰해보려고 한다. RR-DnCNN v2.0 논문에 대한 리뷰는 아래 글을 참고바란다. 2022.0..

[논문 리뷰] CNN-based Motion Compensation

[References] Shuai Huo, Dong Liu, Feng Wu, Houqiang Li, “Convolutional Neural Network-Based Motion Compensation Refinement for Video Coding,” in IEEE International Symposium on Circuits and Systems (ISCAS), 2018, pp. 1–4. Zhenghui Zhao, Shiqi Wang, Shanshe Wang, Xinfeng Zhang, Siwei Ma, Jiansheng Yang, “CNN-Based Bi-Directional Motion Compensation for High Efficiency Video Coding,” in IEEE Inter..

[논문 리뷰] Affine Motion Compensation Prediction

[References] M. Narroschke and R. Swoboda, “Extending hevc by an affine motion model,” in 2013 Picture Coding Symposium (PCS), Dec 2013, pp. 321–324. H. Huang, J. Woods, Y. Zhao, and H. Bai, “Affine skip and direct modes for efficient video coding,” in Visual Communications and Image Processing (VCIP), 2012 IEEE, Nov. 2012, pp. 1–6. L. Li, H. Li, D. Liu, Z. Li, H. Yang, L. Sixin, H. Chen, and F...