# GeoMag: Geometric-Aware Video Motion Magnification via State Space Model

arXiv: https://arxiv.org/abs/2605.29762 · HTML: https://mlsanity.com/paper/2605.29762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 15 of 15)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Audio-Visual Segmentation](https://mlsanity.com/paper/2207.05042/) (2022)
- [Learning-based Video Motion Magnification](https://mlsanity.com/paper/1804.02684/) (2018)
- [Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture](https://mlsanity.com/paper/2403.07347/) (2024)
- [EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer](https://mlsanity.com/paper/2312.04152/) (2023)
- [COCONut: Modernizing COCO Segmentation](https://mlsanity.com/paper/2404.08639/) (2024)
- [Self-Supervised Motion Magnification by Backpropagating Through Optical Flow](https://mlsanity.com/paper/2311.17056/) (2023)
- [The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts](https://mlsanity.com/paper/2505.17476/) (2025)
- [STB-VMM: Swin Transformer Based Video Motion Magnification](https://mlsanity.com/paper/2302.10001/) (2023)
- [Learning-based Axial Video Motion Magnification](https://mlsanity.com/paper/2312.09551/) (2023)
- [RMES: Real-Time Micro-Expression Spotting Using Phase From Riesz Pyramid](https://mlsanity.com/paper/2305.05523/) (2023)
- [Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection](https://mlsanity.com/paper/2603.01993/) (2026)

## Abstract (arXiv)

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.