3D运动放大：利用时间变化的辐射场可视化微小运动

摘要

运动放大帮助我们可视化微小、难以察觉的运动。然而，先前的方法仅适用于由固定摄像头拍摄的2D视频。我们提出了一种3D运动放大方法，可以放大由移动摄像头捕捉的场景中微小的运动，同时支持新颖的视角渲染。我们用时间变化的辐射场表示场景，并利用欧拉原理进行运动放大，以提取和放大固定点的嵌入随时间变化的差异。我们研究并验证了我们提出的3D运动放大原理，使用隐式和三平面辐射场作为我们的基础3D场景表示。我们评估了我们的方法在各种摄像头设置下捕捉的合成和真实场景的有效性。

English

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.

3D运动放大：利用时间变化的辐射场可视化微小运动

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

摘要

Support