YODA用单步扩散模型实现视频压缩，提升画质同时减少文件大小。
YODA: Yet Another One-step Diffusion-based Video Compressor
- 引入时序参考特征，联合建模空间与时间相关性。
- 在LPIPS、DISTS等指标上超越传统和深度学习基线。
- 适合关注高效视频压缩与高质量生成的开发者。
尽管单步扩散模型在感知图像压缩方面表现优异，但其在视频压缩中的应用仍有限。以往方法通常依赖预训练的2D自编码器独立生成每帧潜在表示，忽略了时间依赖性。本文提出YODA——一种基于单步扩散的视频压缩框架，通过嵌入多尺度时序参考特征来生成和编码潜在表示，更充分地利用时空相关性以获得更紧凑的表达，并采用线性扩散Transformer（DiT）实现高效的单步去噪。YODA在LPIPS、DISTS、FID和KID等指标上持续优于传统及深度学习基线。源代码将公开于https://github.com/NJUVISION/YODA。
原文摘要 · Abstract (English)
While one-step diffusion models have recently excelled in perceptual image compression, their application to video remains limited. Prior efforts typically rely on pretrained 2D autoencoders that generate per-frame latent representations independently, thereby neglecting temporal dependencies. We present YODA--Yet Another One-step Diffusion-based Video Compressor--which embeds multiscale features from temporal references for both latent generation and latent coding to better exploit spatial-temporal correlations for more compact representation, and employs a linear Diffusion Transformer (DiT) for efficient one-step denoising. YODA achieves state-of-the-art perceptual performance, consistently outperforming traditional and deep-learning baselines on LPIPS, DISTS, FID, and KID. Source code will be publicly available at https://github.com/NJUVISION/YODA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。