CoordFlow：面向像素级神经视频表示的坐标流
CoordFlow: Coordinate Flow for Pixel-wise Neural Video Representation
AI总结：
本文提出 CoordFlow，一种逐像素隐式神经表示视频压缩方法，通过将视频分解为视觉一致层并利用运动轨迹补偿冗余，在性能上达到逐像素 INR 最优并与逐帧方法相当，同时具备无监督分割、超分辨率、稳定、修复和去噪等能力。
摘要：
在视频压缩领域，以更低码率追求更高质量始终是一个长期目标。近期进展表明，隐式神经表示（Implicit Neural Representation, INR）有望成为传统基于变换的方法的一种有前景的替代方案。根据网络输出结构，视频 INR 可大致分为逐帧方法和逐像素方法。虽然基于像素的方法在超分辨率和并行化方面更具优势，但逐帧方法表现出更好的性能。我们提出 CoordFlow，一种用于视频压缩的新型逐像素 INR。与其他逐像素 INR 相比，它取得了最先进的结果，并且与领先的逐帧技术相比性能相当。该方法基于将视觉信息分离为视觉上一致的层，每一层由一个专用网络表示，该网络补偿该层的运动。在集成时，其副产品是视频序列的无监督分割。物体运动轨迹被隐式利用以补偿视觉-时间冗余。此外，所提出的方法提供了固有的视频超分辨率、稳定、修复和去噪能力。
英文摘要：
In the field of video compression, the pursuit for better quality at lower bit rates remains a long-lasting goal. Recent developments have demonstrated the potential of Implicit Neural Representation (INR) as a promising alternative to traditional transform-based methodologies. Video INRs can be roughly divided into frame-wise and pixel-wise methods according to the structure the network outputs. While the pixel-based methods are better for upsampling and parallelization, frame-wise methods demonstrated better performance. We introduce CoordFlow, a novel pixel-wise INR for video compression. It yields state-of-the-art results compared to other pixel-wise INRs and on-par performance compared to leading frame-wise techniques. The method is based on the separation of the visual information into visually consistent layers, each represented by a dedicated network that compensates for the layer's motion. When integrated, a byproduct is an unsupervised segmentation of video sequence. Objects motion trajectories are implicitly utilized to compensate for visual-temporal redundancies. Additionally, the proposed method provides inherent video upsampling, stabilization, inpainting, and denoising capabilities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
