arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.01554cs.CVcs.GR
收藏

来自单眼RGB视频的神经头化身

Neural Head Avatars from Monocular RGB Videos

Heidelberg University(海德堡大学);Technical University of Munich(慕尼黑工业大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Philip-William Grassal, Malte Prinzler, Titus Leistner, Carsten Rother, Matthias Nießner, Justus Thies

摘要:

我们提出了神经头化身,这是一种新型的神经表示,它明确地对可动画化的人类化身的表面几何形状和外观进行建模,可用于AR/VR中的电话会议或依赖于数字人的电影或游戏行业中的其他应用。我们的表示可以从具有一系列不同表情和视图的单目RGB肖像视频中学习。具体来说,我们提出了一个混合表示的变形模型的粗糙形状和表情的脸,和两个前馈网络,预测底层网格的顶点偏移以及视图和表情相关的纹理。我们证明,这种表示是能够准确地外推到看不见的姿势和视点,并生成自然的表情,同时提供尖锐的纹理细节。与以前的头部化身的作品相比,我们的方法提供了一个完整的人类头部(包括头发),与标准的图形管道兼容的解开的形状和外观模型。此外,它在定量和定性方面优于当前最先进的重建质量和新颖的视图合成。

英文摘要:

We present Neural Head Avatars, a novel neural representation that explicitly models the surface geometry and appearance of an animatable human avatar that can be used for teleconferencing in AR/VR or other applications in the movie or games industry that rely on a digital human. Our representation can be learned from a monocular RGB portrait video that features a range of different expressions and views. Specifically, we propose a hybrid representation consisting of a morphable model for the coarse shape and expressions of the face, and two feed-forward networks, predicting vertex offsets of the underlying mesh as well as a view- and expression-dependent texture. We demonstrate that this representation is able to accurately extrapolate to unseen poses and view points, and generates natural expressions while providing sharp texture details. Compared to previous works on head avatars, our method provides a disentangled shape and appearance model of the complete human head (including hair) that is compatible with the standard graphics pipeline. Moreover, it quantitatively and qualitatively outperforms current state of the art in terms of reconstruction quality and novel-view synthesis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑