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.
@article{arxiv.2601.01141,
title = {YODA: Yet Another One-step Diffusion-based Video Compressor},
author = {Xingchen Li and Junzhe Zhang and Junqi Shi and Ming Lu and Zhan Ma},
journal= {arXiv preprint arXiv:2601.01141},
year = {2026}
}
Comments
Code will be available at https://github.com/NJUVISION/YODA