GeoMag: Geometric-Aware Video Motion Magnification via State Space Model
For researchers and practitioners in video motion magnification, GeoMag addresses the trade-off between global context and computational cost, improving structural consistency under complex geometric transformations.
GeoMag introduces a geometric-aware video motion magnification framework using State Space Models to achieve globally consistent motion amplification with linear complexity, and constructs a large-scale synthetic dataset Geo-200K with rich geometric transformations and realistic degradations. It consistently outperforms prior methods in visual fidelity and computational efficiency, producing fewer artifacts and better structural consistency.
Video Motion Magnification (VMM) reveals imperceptible dynamics but often suffers from structural inconsistencies under complex geometric transformations. Existing learning-based methods generally face a trade-off between the limited global context of CNNs and the high computational cost of Transformers. In addition, current training protocols, largely dominated by simple linear motion, fail to capture the geometric and imaging complexities encountered in real-world videos. To address these issues, we propose GeoMag, a geometric-aware VMM framework built upon State Space Models to achieve globally consistent motion amplification with linear complexity. We further construct Geo-200K, a large-scale synthetic dataset that introduces rich geometric transformations together with sensor-realistic degradations, improving the diversity and realism of training signals. Extensive experiments on synthetic and real-world benchmarks show that GeoMag consistently outperforms prior methods in visual fidelity and computational efficiency, while producing fewer artifacts and better structural consistency.