标题: 【SIGGRAPH Asia 2012专题*技术论文】图像操作：换装！通过自动优化的装备合成 [打印本页] 作者: . 时间: 2012-12-14 16:55 标题: 【SIGGRAPH Asia 2012专题*技术论文】图像操作：换装！通过自动优化的装备合成 【SIGGRAPH Asia 2012专题*技术论文】
图像操作：换装！通过自动优化的装备合成
DressUp! Outfit Synthesis Through Automatic Optimization
Lap-Fai Yu, Sai-Kit Yeung, Demetri Terzopoulos, Tony F. Chan
摘要：我们提出一个自动优化方法合成出?。由于头发的颜色，眼睛的颜色，皮肤颜色的放在身体，加上一个衣橱服饰用品，我们?合成系统，提出了一套出?是受特定着装。我们介绍的概率框架建模和应用规范，利用贝叶斯网络的训练，例如图像的真实了?指标。适合了?指标得到优化成本函数，指导选择的服装项目最大限度的颜色的兼容性和着装适宜性。我们证明我们的方法对四种最常见的着装：休闲，运动装，商务休闲装，和业务。知觉研究验证了其多种合力?表明，英法?卡框架。
Abstract：We present an automatic optimization approach to out?t synthesis. Given the hair color, eye color, and skin color of the in put body, plus a wardrobe of clothing items, our out?t synthesis system suggests a set of out?ts subject to a particular dress code. We in troduce a probabilistic framework for modeling and applying dress codes that exploits a Bayesian network trained on example images of real-world out?ts. Suitable out?ts are then obtained by optimizing a cost function that guides the selection of clothing items to maximize the color compatibility and dress code suitability. We demonstrate our approach on the four most common dress codes:Casual,Sportswear, Business-Casual, and Business. A perceptual study validated on multiple resultant out?ts demonstrates the ef?cacy of our framework.
要了解该论文的详情呢，就下载附件好好研究一下哈~更多新技术分享尽在Web3D纳金网http://www.narkii.com/作者: mandonggua 时间: 2017-6-8 11:21
谢谢分享。