Video stabilization aims to mitigate camera shake but faces a fundamental trade-off between geometric robustness and full-frame consistency. While 2D methods suffer from aggressive cropping, 3D techniques are often undermined by fragile optimization pipelines that fail under extreme motions. To bridge this gap, we propose VS3R, a framework that synergizes feed-forward 3D reconstruction with generative video diffusion. Our pipeline jointly estimates camera parameters, depth, and masks to ensure all-scenario reliability, and introduces a Hybrid Stabilized Rendering module that fuses semantic and geometric cues for dynamic consistency. Finally, a Dual-Stream Video Diffusion Model restores disoccluded regions and rectifies artifacts by synergizing structural guidance with semantic anchors. Collectively, VS3R achieves high-fidelity, full-frame stabilization across diverse camera models and significantly outperforms state-of-the-art methods in robustness and visual quality.
@article{arxiv.2603.05851,
title = {VS3R: Robust Full-frame Video Stabilization via Deep 3D Reconstruction},
author = {Muhua Zhu and Xinhao Jin and Yu Zhang and Yifei Xue and Tie Ji and Yizhen Lao},
journal= {arXiv preprint arXiv:2603.05851},
year = {2026}
}