OmnimatteRF：具備3D背景建模的穩健Omnimatte

摘要

影片抠像具有广泛的应用，从为随意拍摄的电影添加有趣的效果到协助视频制作专业人员。带有阴影和反射等相关效果的抠像也吸引了越来越多的研究活动，提出了诸如Omnimatte之类的方法，将动态前景对象分离为其自己的图层。然而，先前的作品将视频背景表示为2D图像图层，限制了它们表达更复杂场景的能力，从而阻碍了对真实世界视频的应用。在本文中，我们提出了一种新颖的视频抠像方法，OmnimatteRF，结合了动态的2D前景图层和一个3D背景模型。2D图层保留了主体的细节，而3D背景则稳健地重建了真实世界视频中的场景。大量实验证明，我们的方法在各种视频上重建出更高质量的场景。

English

Video matting has broad applications, from adding interesting effects to casually captured movies to assisting video production professionals. Matting with associated effects such as shadows and reflections has also attracted increasing research activity, and methods like Omnimatte have been proposed to separate dynamic foreground objects of interest into their own layers. However, prior works represent video backgrounds as 2D image layers, limiting their capacity to express more complicated scenes, thus hindering application to real-world videos. In this paper, we propose a novel video matting method, OmnimatteRF, that combines dynamic 2D foreground layers and a 3D background model. The 2D layers preserve the details of the subjects, while the 3D background robustly reconstructs scenes in real-world videos. Extensive experiments demonstrate that our method reconstructs scenes with better quality on various videos.

OmnimatteRF：具備3D背景建模的穩健Omnimatte

OmnimatteRF: Robust Omnimatte with 3D Background Modeling

摘要

Support