基于颜色分离与排序链的感知神经视频压缩
Perceptual Neural Video Compression with Color Separation and Rank Chain
把亮度与色度解耦处理并分别分配计算与码率预算，再配合基于码率的排序链损失做感知优化，这套思路可直接迁移到任何需要兼顾保真度与感知质量的低层视觉编码/复原任务中。
原文依据 we propose a color-separation-based framework, termed PNVC-C, which decouples luminance and chrominance processing
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论神经视频压缩（NVC）近年来取得了显著进展。以深度条件视频编码系列为代表的最优 NVC 方案主要致力于追求更高的保真度（如 PSNR），但未能充分利用深度网络在提升感知质量方面的优势。我们以两项新技术填补这一空白。首先，我们提出一种基于颜色分离的框架，称为 PNVC-C，它将亮度与色度处理解耦，从而更好地契合人类视觉感知。该框架能够在亮度与色度分量之间显式且自适应地分配计算与码率预算。其次，在该框架内，我们引入感知优化方案 Rc-GAN，它利用基于码率的排序链损失将可变码率编码与感知质量排序关联起来，强制保持一致的质量顺序并提升感知保真度。基于这些设计，我们建立了 PNVC-C 框架并给出两个变体：PNVC-C-Base 针对客观保真度优化，PNVC-CR 是应用 Rc-GAN 的感知变体。实验结果表明，PNVC-C-Base 在 YUV PSNR 上达到最优的客观性能，而 PNVC-CR 在 LPIPS、DISTS、KID 和弗雷歇初始距离指标上达到最优的感知质量。源代码已发布于 https://github.com/lxz-nan/PNVC-CR。
英文原文摘要 1383 字符
Neural video compression (NVC) has achieved significant progress in recent years. The state-of-the-art (SOTA) NVC schemes, exemplified by the Deep Conditional Video Coding series, have focused on pursuing higher fidelity (e.g., PSNR), but lack sufficient exploitation of deep networks' advantages for better perceptual quality. We fill in this gap with two new techniques. First, we propose a color-separation-based framework, termed PNVC-C, which decouples luminance and chrominance processing to better align with human visual perception. This framework enables explicit and adaptive allocation of computation and bitrate budgets between luminance and chrominance components. Second, within this framework, we introduce the perceptual optimization scheme Rc-GAN, which leverages a bitrate-based rank chain loss to link variable-rate coding with perceptual quality ranking, enforcing consistent quality ordering and improving perceptual fidelity. Built upon these designs, we establish the PNVC-C framework with two variants: PNVC-C-Base, optimized for objective fidelity, and PNVC-CR, a perceptual variant that applies the Rc-GAN. Experimental results demonstrate that PNVC-C-Base achieves SOTA objective performance in YUV PSNR, while PNVC-CR attains SOTA perceptual quality on LPIPS, DISTS, KID, and FID metrics. The source code is released at https://github.com/lxz-nan/PNVC-CR.