[2506.08862] StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams

Computer Science > Computer Vision and Pattern Recognition arXiv:2506.08862 (cs) [Submitted on 10 Jun 2025 (v1), last revised 2 Mar 2026 (this version, v2)] Title:StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams Authors:Zike Wu, Qi Yan, Xuanyu Yi, Lele Wang, Renjie Liao View a PDF of the paper titled StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams, by Zike Wu and 4 other authors View PDF HTML (experimental) Abstract:Real-time reconstruction of dynamic 3D scenes from uncalibrated video streams demands robust online methods that recover scene dynamics from sparse observations under strict latency and memory constraints. Yet most dynamic reconstruction methods rely on hours of per-scene optimization under full-sequence access, limiting practical deployment. In this work, we introduce StreamSplat, a fully feed-forward framework that instantly transforms uncalibrated video streams of arbitrary length into dynamic 3D Gaussian Splatting (3DGS) representations in an online manner. It is achieved via three key technical innovations: 1) a probabilistic sampling mechanism that robustly predicts 3D Gaussians from uncalibrated inputs; 2) a bidirectional deformation field that yields reliable associations across frames and mitigates long-term error accumulation; 3) an adaptive Gaussian fusion operation that propagates persistent Gaussians while handling emerging and vanishing ones. Extensive experiments on standa...