Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Muhua Zhu, Xinhao Jin, Yu Zhang, Yifei Xue, Tie Ji, Yizhen Lao• 2026

Related benchmarks

TaskDatasetResultRank
Video StabilizationNUS Average of All Categories
Cropping100
8
Video StabilizationNUS Running
Cropping100
8
Video StabilizationNUS (Crowd)
Cropping Score99.9
8
Video StabilizationNUS Parallax
Cropping100
8
Video StabilizationNUS Zooming
Cropping Quality100
8
Video StabilizationNUS (Rotation)
Cropping Quality99.9
8
Video StabilizationNUS (Regular)
Cropping Quality100
8
Showing 7 of 7 rows

Other info

Follow for update