VS3R: Robust Full-frame Video Stabilization via Deep 3D Reconstruction
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Video Stabilization | NUS Average of All Categories | Cropping100 | 8 | |
| Video Stabilization | NUS Running | Cropping100 | 8 | |
| Video Stabilization | NUS (Crowd) | Cropping Score99.9 | 8 | |
| Video Stabilization | NUS Parallax | Cropping100 | 8 | |
| Video Stabilization | NUS Zooming | Cropping Quality100 | 8 | |
| Video Stabilization | NUS (Rotation) | Cropping Quality99.9 | 8 | |
| Video Stabilization | NUS (Regular) | Cropping Quality100 | 8 |