生成式视频压缩的信息容量：量化相同质量下的码率-计算量交换
Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality
- Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究院（TeleAI））
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出信息容量指标，量化生成式视频压缩中码率与计算量的交换效率，发现14B解码器比1.3B解码器节省码率效率高约十倍，且该指标随数据集变化显著。
AI中文摘要：
在AI Flow框架下，通信网络将智能分布在设备、边缘服务器和云端之间，接收端的计算成为一种可替代传输比特的资源。生成式视频压缩（GVC）通过发送超低码率的紧凑令牌并让生成式解码器合成视频来体现这种交换，然而单位解码器计算究竟能带来多少带宽节省从未被量化。为填补这一空白，我们将重建质量建模为数据速率和计算量的双因子幂律，该模型对两个GVC解码器的实测DISTS拟合平均误差低于3%，并将信息容量（IC）定义为等质量轮廓线上的负对数斜率，即在相同质量下，计算量每增加一个分数所节省的码率分数。IC是无量纲且单位不变的，因此能够实现与架构无关的比较。它在工作平面上形成一个场，定位额外去噪步骤值得其成本的区域。在五个数据集上，14B解码器以约十倍于1.3B解码器的效率用更多计算换取更少码率。IC在不同数据集间也显著变化，表明GVC方法在码率-计算量权衡上存在不均衡的表现。
英文摘要：
Under the AI Flow framework, communication networks distribute intelligence across devices, edge servers, and clouds, and computation at the receiver becomes a resource that can substitute for transmitted bits. Generative video compression (GVC) embodies this exchange by sending compact tokens with ultra-low bitrate and letting a generative decoder synthesize the video, yet how much bandwidth savings a unit of decoder compute actually achieves has never been quantified. To fill this vacancy, we model reconstruction quality as a two-factor power law in data rate and decoder compute, which fits measured DISTS of two GVC decoders with a mean error below 3%, and define the information capacity (IC) as the negative logarithmic slope along an iso-quality contour, namely the fraction of rate saved per fractional increase in compute at identical quality. IC is dimensionless and unit-invariant, thus enabling an architecture-agnostic comparison. It forms a field over the operating plane, locating where additional denoising steps are worth their cost. Across five datasets, the 14B decoder trades more compute for fewer rate about ten times more efficiently than the 1.3B decoder. IC also varies significantly across datasets, indicating imbalanced performance on the rate-compute trade-off in GVC methods.
