ChatPaper.aiChatPaper

3D運動放大:利用時間變化的輻射場來視覺化微妙運動

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

August 7, 2023
作者: Brandon Y. Feng, Hadi Alzayer, Michael Rubinstein, William T. Freeman, Jia-Bin Huang
cs.AI

摘要

運動放大有助於我們視覺化微妙、難以察覺的運動。然而,先前的方法僅適用於由固定攝影機拍攝的二維影片。我們提出了一種三維運動放大方法,可以放大由移動攝影機拍攝的場景中微妙的運動,同時支援新穎的視角渲染。我們用時間變化的輝度場來表示場景,並利用歐拉原理進行運動放大,以提取並放大固定點隨時間變化的嵌入變化。我們使用隱式和三平面為基礎的輝度場作為底層三維場景表示,研究並驗證了我們提出的三維運動放大原理。我們在合成和真實場景上評估了我們的方法在不同攝影機配置下的有效性。
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.
PDF120December 15, 2024