Abstract
Real-time video super-resolution requires high spatio-temporal fidelity under strict latency constraints, challenging diffusion models due to their iterative sampling cost and limited temporal coordination. We propose a streaming-aware framework that adapts pretrained single-image latent diffusion models for efficient video super-resolution (VSR) by exploiting the sequential structure of video streams. Our Cross-Step Attention mechanism reuses intermediate denoising features across adjacent frames and diffusion steps, enabling temporal information exchange without explicit temporal modeling. We further introduce Trajectory-Coupled Diffusion Scheduling, which aligns adjacent diffusion states and provides cleaner intermediate representations for cross-step conditioning, improving temporal coherence. These components are integrated into a streaming inference pipeline that incrementally propagates latent states across frames, reducing the effective computational complexity from $O(N \cdot S)$ to $O(N + S)$ for $N$ frames and $S$ diffusion steps. Experiments on REDS4 and YouHQ40-Test demonstrate improved perceptual quality and temporal realism while maintaining frame-wise stability. Our method achieves over 40 FPS at $512 \times 512$ resolution after cold start, enabling real-time VSR without explicit temporal modeling.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Partaourides, H., & Chatzis, S. (2026). Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention. https://omanscience.com/en/articles/streaming-aware-diffusion-for-real-time-video-super-resolution-via-cross-step-attention
MLA 9
Partaourides, Harris, and Sotirios Chatzis. "Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention." https://omanscience.com/en/articles/streaming-aware-diffusion-for-real-time-video-super-resolution-via-cross-step-attention.
Chicago (author–date)
Partaourides, Harris, and Sotirios Chatzis. 2026. "Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention." https://omanscience.com/en/articles/streaming-aware-diffusion-for-real-time-video-super-resolution-via-cross-step-attention.
Harvard
Partaourides, H. and Chatzis, S. (2026) 'Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention', Available at: https://omanscience.com/en/articles/streaming-aware-diffusion-for-real-time-video-super-resolution-via-cross-step-attention.
Vancouver
Partaourides H, Chatzis S. Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention. https://omanscience.com/en/articles/streaming-aware-diffusion-for-real-time-video-super-resolution-via-cross-step-attention
IEEE
H. Partaourides, and S. Chatzis, "Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention," https://omanscience.com/en/articles/streaming-aware-diffusion-for-real-time-video-super-resolution-via-cross-step-attention.