Thangka Mural Line Drawing Based on Cross Dense Residual Architecture and Hard Pixel Balancing
Thangka Mural Line Drawing Based on Cross Dense Residual Architecture and Hard Pixel Balancing
复制标题
基于交叉密集残差结构和硬像素平衡的唐卡壁画线描
DOI：
10.1109/access.2021.3068199
复制
发表时间：
2021
期刊：
影响因子：
3.9
通讯作者：
Wenjin Hu
中科院分区：
文献类型：
--
作者：
Nianyi Wang;Weilan Wang;Wenjin Hu
唐卡壁画是西藏珍贵的历史、文学、艺术文化遗产，唐卡壁画数字线描不仅是唐卡艺术欣赏的抽象表达，也是唐卡保护的基础数字资源。数字唐卡线描画属于图像边缘检测，它是计算机视觉的一个基本问题，其目的是从图像中提取视觉上显著的边缘。各种高级计算机视觉任务都依赖于边缘检测。虽然现有的非学习和基于学习的边缘检测方法已经取得了进展，他们未能产生语义上合理的薄边缘，特别是薄的物体边缘。提出了一种新的深度监督边缘检测解决方案--Richer In-object Thin Edge Network（RITE-Net），用于唐卡壁画图像的线条画生成。与现有研究相比，首先，提出了一种新的交叉密集残差结构（CDR），使用长距离特征存储器将丰富的边缘特征有效地从CNN的浅层传播到深层;其次，设计了一种新的基于硬像素平衡（HPB）的损失函数策略，专注于硬像素的消除。在不同数据集上的实验和测试表明，与现有的方法相比，所提出的RITE-Net能够产生视觉上更合理和更丰富的薄边缘图。客观和主观评价都验证了我们的方法的竞争力。
Thangka murals are precious cultural heritage for Tibetan history, literature, and art. Digital line drawing of Thangka murals plays a vital role not only as an abstracted expression of Thangka for art appreciation but also as a fundamental digital resource for Thangka protection. Digital Thangka line drawing can be categorized as image edge detection, which as a fundamental problem for computer vision, aims to extract visually salient edges from images. Varieties of high-level computer vision tasks depend on edge detection. Although existing non-learning and learning-based edge detection methods have progressed, they failed to generate semantically plausible thin edges, especially thin in-object edges. We propose a novel deep supervised edge detection solution Richer In-object Thin Edge Network (RITE-Net) to generate line drawings of Thangka mural images. Compared to existing studies, firstly a new Cross Dense Residual architecture (CDR) is proposed to propagate abundant edge features effectively from shallow layers to deep layers of CNN using a long-range feature memory; Secondly, a new Hard Pixel Balancing (HPB) based loss function strategy is designed to focus on hard pixel distinguishment. Experiments and tests on different datasets show that the proposed RITE-Net is able to produce more visually plausible and richer thin edge maps comparing to the existing methods. Both objective and subjective evaluations validated the competitive performance of our method.
登录
查看更多内容
影响因子：
19.5
作者：
Xie, Saining;Tu, Zhuowen
通讯作者：
Tu, Zhuowen
DOI：
--
发表时间：
2012-12
期刊：
--
影响因子：
--
作者：
Xiaofeng Ren;Liefeng Bo
通讯作者：
Xiaofeng Ren;Liefeng Bo
DOI：
10.1109/tpami.2014.2377715
发表时间：
2015-08-01
影响因子：
23.6
作者：
Dollar, Piotr;Zitnick, C. Lawrence
通讯作者：
Zitnick, C. Lawrence
影响因子：
10.6
作者：
Grigorescu, C;Petkov, N;Westenberg, MA
通讯作者：
Westenberg, MA
DOI：
10.1109/tpami.2018.2858826
发表时间：
2020-02-01
影响因子：
23.6
作者：
Lin, Tsung-Yi;Goyal, Priya;Dollar, Piotr
通讯作者：
Dollar, Piotr