HAO‐CNN: Filament‐aware hair reconstruction based on volumetric vector fields,Computer Animation and Virtual Worlds

当前位置： X-MOL 学术 › Comput. Animat. Virtual Worlds › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

HAO‐CNN: Filament‐aware hair reconstruction based on volumetric vector fields
Computer Animation and Virtual Worlds ( IF 0.9 ) Pub Date : 2020-07-01 , DOI: 10.1002/cav.1945
Zehao Ye ₁ , Guiqing Li ₁ , Biyuan Yao ₁ , Chuhua Xian ₁

Affiliation

Hair modeling plays an important role in computer animation, virtual reality, and other applications. This paper proposes an encoder‐decoder network, named HAO‐CNN, to recover 3D hair strand models from a single image. Specifically, HAO‐CNN generates a volumetric vector field (VVF) from the oriented map of hairstyles. However, instead of directly working on the full resolution VVFs, we introduce the adapted O‐CNN to predict the adaptive representation of VVFs in order to greatly reduce the memory cost. In addition, we fuse the features from different layers of the encoding stage for both capturing the global structure and being aware of hair filaments. Considering the difficulty of acquiring true three‐dimensional (3D) hair models, we augment the dataset with 340 3D hair models by 1,800 hair models via interactive editing using the software and render their oriented maps as training data. Then given a hair photo associated with human head, we segment out the hair region, compute its two‐dimensional oriented map using Gabor filter, and feed it into the network to produce a hair volumetric vector field which is then converted into hairline models using an improved VVF‐to‐strands algorithm. This greatly decreases the time cost of approaches based on volumetric vector fields.

中文翻译：

HAO-CNN：基于体积向量场的细丝感知头发重建

头发造型在计算机动画、虚拟现实和其他应用中扮演着重要的角色。本文提出了一种名为 HAO-CNN 的编码器-解码器网络，用于从单个图像中恢复 3D 发束模型。具体来说，HAO-CNN 从发型的定向图生成体积向量场 (VVF)。然而，我们不是直接在全分辨率 VVF 上工作，而是引入了自适应 O-CNN 来预测 VVF 的自适应表示，以大大降低内存成本。此外，我们融合了来自编码阶段不同层的特征，以捕获全局结构并了解发丝。考虑到获取真正的三维（3D）头发模型的难度，我们将 340 个 3D 头发模型的数据集增加 1，使用该软件通过交互式编辑 800 个头发模型，并将它们的定向图渲染为训练数据。然后给定一张与人头相关的头发照片，我们分割出头发区域，使用 Gabor 滤波器计算其二维定向图，并将其输入网络以产生头发体积矢量场，然后使用改进的 VVF-to-strands 算法。这大大降低了基于体积矢量场的方法的时间成本。

更新日期：2020-07-01

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11