[
    {
        "id": "osp-17676",
        "type": "article-journal",
        "title": "Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention",
        "author": [
            {
                "family": "Partaourides",
                "given": "Harris"
            },
            {
                "family": "Chatzis",
                "given": "Sotirios"
            }
        ],
        "URL": "https://omanscience.com/en/articles/streaming-aware-diffusion-for-real-time-video-super-resolution-via-cross-step-attention",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]