3D Motion Magnification: Visualizing Subtle Motions with Time Varying Radiance Fields

TL;DR

This paper introduces a novel 3D motion magnification technique that visualizes subtle motions in scenes captured with moving cameras, utilizing time-varying radiance fields for both scene representation and motion amplification.

Contribution

It presents a new method combining radiance fields and the Eulerian principle to magnify subtle 3D motions from moving camera captures, supporting novel view rendering.

Findings

Effective on synthetic scenes

Validated on real-world scenes

Supports moving camera setups

Abstract

Motion magnification helps us visualize subtle, imperceptible motion. However, prior methods only work for 2D videos captured with a fixed camera. We present a 3D motion magnification method that can magnify subtle motions from scenes captured by a moving camera, while supporting novel view rendering. We represent the scene with time-varying radiance fields and leverage the Eulerian principle for motion magnification to extract and amplify the variation of the embedding of a fixed point over time. We study and validate our proposed principle for 3D motion magnification using both implicit and tri-plane-based radiance fields as our underlying 3D scene representation. We evaluate the effectiveness of our method on both synthetic and real-world scenes captured under various camera setups.