3D Motion Magnification: Visualizing Subtle Motions with Time Varying Radiance Fields
This enables motion magnification for dynamic scenes with moving cameras, benefiting applications like medical imaging or structural analysis, though it is incremental as it extends existing principles to 3D.
The paper tackles the problem of visualizing subtle motions in scenes captured by moving cameras, which prior 2D methods could not handle, and achieves this by developing a 3D motion magnification method that supports novel view rendering, validated on synthetic and real-world scenes.
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.