1
GeoMag: Geometric-Aware Video Motion Magnification via State Space Model
结合几何感知与状态空间模型，首次在视频运动放大中兼顾细微运动和形状保留，ICME 2026 Spotlight论文
arXiv:2605.29762v1 Announce Type: new Abstract: Video Motion Magnification (VMM) reveals imperceptible dynamics but often suffers from structural inco…