تقرير
I M Avatar: Implicit Morphable Head Avatars from Videos
العنوان: | I M Avatar: Implicit Morphable Head Avatars from Videos |
---|---|
المؤلفون: | Zheng, Yufeng, Abrevaya, Victoria Fernández, Bühler, Marcel C., Chen, Xu, Black, Michael J., Hilliges, Otmar |
سنة النشر: | 2021 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
الوصف: | Traditional 3D morphable face models (3DMMs) provide fine-grained control over expression but cannot easily capture geometric and appearance details. Neural volumetric representations approach photorealism but are hard to animate and do not generalize well to unseen expressions. To tackle this problem, we propose IMavatar (Implicit Morphable avatar), a novel method for learning implicit head avatars from monocular videos. Inspired by the fine-grained control mechanisms afforded by conventional 3DMMs, we represent the expression- and pose- related deformations via learned blendshapes and skinning fields. These attributes are pose-independent and can be used to morph the canonical geometry and texture fields given novel expression and pose parameters. We employ ray marching and iterative root-finding to locate the canonical surface intersection for each pixel. A key contribution is our novel analytical gradient formulation that enables end-to-end training of IMavatars from videos. We show quantitatively and qualitatively that our method improves geometry and covers a more complete expression space compared to state-of-the-art methods. Comment: Accepted at CVPR 2022 as an oral presentation. Project page https://ait.ethz.ch/projects/2022/IMavatarTest/ ; Github page: https://github.com/zhengyuf/IMavatarTest |
نوع الوثيقة: | Working Paper |
الوصول الحر: | http://arxiv.org/abs/2112.07471Test |
رقم الانضمام: | edsarx.2112.07471 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |