arXiv:2202.04365
공식 코드 · Papers with Code
AIVC: Artificial Intelligence based Video Codec
원문 초록
This paper introduces AIVC, an end-to-end neural video codec. It is based on two conditional autoencoders MNet and CNet, for motion compensation and coding. AIVC learns to compress videos using any coding configurations through a single end-to-end rate-distortion optimization. Furthermore, it offers performance competitive with the recent video coder HEVC under several established test conditions. A comprehensive ablation study is performed to evaluate the benefits of the different modules composing AIVC. The implementation is made available at https://orange-opensource.github.io/AIVC/.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation
PD-SORT: Occlusion-Robust Multi-Object Tracking Using Pseudo-Depth Cues
Unsupervised Training of a Dynamic Context-Aware Deep Denoising Framework for Low-Dose Fluoroscopic Imaging
Infrared Small Target Detection in Satellite Videos: A New Dataset and A Novel Recurrent Feature Refinement Framework
One Homography is All You Need: IMM-based Joint Homography and Multiple Object State Estimation
IM-MoCo: Self-supervised MRI Motion Correction using Motion-Guided Implicit Neural Representations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.