Skip to main content
Search

# Video Diffusion Transformers

2 related articles

Subscribe to updates
  1. arXiv

    Streaming video compression stops waiting for whole clips: SGVC turns a video DiT into a causal per-frame refiner, saving 71.97% BD-rate on DISTS

    Generative video compression at ultra-low bitrates leans on pretrained video diffusion transformers, but reconstruction passes through a costly VAE decoder, and jointly refining multiple frames adds buffering delay. SGVC projects decoded codec features straight into the video DiT input embedding space, uses embedding alignment to close the representation gap, and propagates layer-wise K/V states across frames so spatiotemporal priors survive causal frame-by-frame decoding. Across HEVC Class B, UVG and MCL-JCV, SGVC saves an average 71.97% BD-rate on DISTS and 35.94% on LPIPS relative to S2VC.

  2. arXiv

    MPEG-Diffusion spends video-generation compute only where detail matters, speeding denoising on Wan2.1 while staying near full-resolution quality

    Video diffusion transformers generate every region of every frame at one resolution, so attention cost grows with token count, while mixed-resolution generation had sharply degraded video quality and required the high-resolution region in advance. MPEG-Diffusion attributes those failures to shared keys and values, decoder neighbor sensitivity and an externally supplied region, and addresses each with dual-resolution attention, a mixed-resolution decoder and a high-resolution region read off DiT features. On Wan2.1 1.3B and 14B it processes only a fraction of full-resolution tokens, speeds up denoising and beats prior mixed-resolution methods on nearly every metric, with raters preferring it over Phase-Aligned RoPE and Foveated Diffusion.

You’re all caught up