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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Xian, D., Zhou, X., Xiong, Y., Wang, Y., & Yang, M. H. (2026). DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed Video. https://omanscience.com/en/articles/dynstream-online-streaming-4d-gaussian-reconstruction-of-dynamic-worlds-from-unposed-video
MLA 9
Xian, Dingwei, et al. "DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed Video." https://omanscience.com/en/articles/dynstream-online-streaming-4d-gaussian-reconstruction-of-dynamic-worlds-from-unposed-video.
Chicago (author–date)
Xian, Dingwei, Xiaoyu Zhou, Yajiao Xiong, Yongtao Wang, and Ming-Hsuan Yang. 2026. "DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed Video." https://omanscience.com/en/articles/dynstream-online-streaming-4d-gaussian-reconstruction-of-dynamic-worlds-from-unposed-video.
Harvard
Xian, D., Zhou, X., Xiong, Y., Wang, Y. and Yang, M. H. (2026) 'DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed Video', Available at: https://omanscience.com/en/articles/dynstream-online-streaming-4d-gaussian-reconstruction-of-dynamic-worlds-from-unposed-video.
Vancouver
Xian D, Zhou X, Xiong Y, Wang Y, Yang MH. DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed Video. https://omanscience.com/en/articles/dynstream-online-streaming-4d-gaussian-reconstruction-of-dynamic-worlds-from-unposed-video
IEEE
D. Xian, X. Zhou, Y. Xiong, Y. Wang, and M. H. Yang, "DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed Video," https://omanscience.com/en/articles/dynstream-online-streaming-4d-gaussian-reconstruction-of-dynamic-worlds-from-unposed-video.