当前位置: X-MOL 学术Graph. Models › 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.)
Portrait relief generation from 3D Object
Graphical Models ( IF 1.7 ) Pub Date : 2019-02-01 , DOI: 10.1016/j.gmod.2019.01.002
Yu-Wei Zhang , Bei-bei Qin , Yanzhao Chen , Zhongping Ji , Caiming Zhang

Automatic generation of reliefs from 3D objects has received great attention in the past few years. The existing methods, which have been developed for general relief generation, are not suitable to handle portrait models that have distinct geometrical features. In this paper, we present a novel method for portrait relief modeling which takes mesh deformation as the theoretical basis. In a pre-processing stage, we segment the input model into several meaningful regions so that different portrait regions could be separately processed. To emphasize visually important features, we further compute object saliency and apply normal enhancement. Once the projective direction is selected by users, the input object is transformed into a compressed height field, followed by a Laplacian-based mesh deformation to optimize the height field. The fine details, salient features and depth structures could be well constructed in the final relief. Experiments and comparisons with state-of-the-art methods demonstrate the effectiveness of our method.



中文翻译:

从3D对象生成人像浮雕

在过去的几年中,从3D对象自动生成浮雕已引起广泛关注。已开发用于一般浮雕生成的现有方法不适合处理具有独特几何特征的肖像模型。在本文中,我们提出了一种新的肖像浮雕建模方法,该方法以网格变形为理论基础。在预处理阶段,我们将输入模型划分为几个有意义的区域,以便可以分别处理不同的肖像区域。为了强调视觉上重要的功能,我们进一步计算对象显着性并应用法线增强。用户选择了投影方向后,将输入对象转换为压缩的高度场,然后进行基于Laplacian的网格变形以优化高度场。精美的细节,在最终浮雕中可以很好地构造出明显的特征和深度结构。最新技术的实验和比较证明了我们方法的有效性。

更新日期:2019-02-01
down
wechat
bug