[
    {
        "id": "osp-17820",
        "type": "article-journal",
        "title": "DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed Video",
        "author": [
            {
                "family": "Xian",
                "given": "Dingwei"
            },
            {
                "family": "Zhou",
                "given": "Xiaoyu"
            },
            {
                "family": "Xiong",
                "given": "Yajiao"
            },
            {
                "family": "Wang",
                "given": "Yongtao"
            },
            {
                "family": "Yang",
                "given": "Ming-Hsuan"
            }
        ],
        "URL": "https://omanscience.com/en/articles/dynstream-online-streaming-4d-gaussian-reconstruction-of-dynamic-worlds-from-unposed-video",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Online reconstruction of dynamic 4D scenes from long, unposed streaming videos requires both continuous processing and photorealistic rendering, which existing methods struggle to achieve simultaneously. Existing feed-forward Gaussian methods are restricted to offline processing, whereas online point-cloud approaches struggle to maintain dense geometry and high-fidelity rendering. We present DynStream, a framework for streaming 4D Gaussian reconstruction from long, unposed videos. Given a continuous video stream, DynStream reconstructs the scene within local temporal windows and incrementally aligns and fuses these local reconstructions into a globally consistent scene, enabling online 4D reconstruction without per-scene optimization. By jointly enforcing cross-window geometric consistency and modeling time-varying scene content, DynStream supports efficient reconstruction and photorealistic rendering over extended video streams. Experiments demonstrate that DynStream enables high-fidelity online dynamic reconstruction and rendering from long video streams, achieving state-of-the-art performance across diverse dynamic indoor and outdoor scenes."
    }
]