3-Sweep_userstudy.pdfVIP

  1. 1、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。。
  2. 2、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载
  3. 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
  4. 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
  5. 5、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们
  6. 6、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
  7. 7、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
3-Sweep_userstudy

User Studies for 3-Sweep? 1 User Study This supplemental file provides detailed statistics of the user study and screenshots of users’ modeling results. In this user study, ten subjects were selected. Eight of them are undergraduate students majoring in computer science and electrical engineering while the other two are artists who are experienced in 3D modeling. Seven among the eight students are novices to 3D object modeling while the other one (S8) is interested in geometry processing and has modeling experience. Between the artists, one is professional in 3DMax and the other is professional in Blender. We provided 13 images for them and split the images into three sets. Set I consists of four images in which the objects are very simple shapes and can be represented by single primitives. Set II contains seven photos which are more complex. Objects in these photos have several parts but the constraints are rather simple. Set III has two photos, and several constraints should be added in the modeling process. We let the eight students and the two artists model the shapes in all the three sets. We asked the artists to load the images into the commercial softwares and try to model the objects as close as possible. Each of the students was given a five-minute instruction of our system. During their modeling process, we recorded the time they used and saved their modeling results. We list the modeling time and modeling results below. Each model was presented to five evaluators (not selected as subjects) and their average scores are used. The evaluators do not know which model comes from which subject. We measured the quality of each model by a subjective score ranging from 1 to 5. Scores: 5 = very good, precise; 4 = good, but with slightly noticeable artifacts; 3 = obvious artifacts, but still acceptable; 2 = very obvious artifacts, not quite acceptable; 1 = very bad, unacceptable. We list modeling results and statistics below. For all the modeling results in the figur

文档评论(0)

l215322 + 关注
实名认证
文档贡献者

该用户很懒,什么也没介绍

1亿VIP精品文档

相关文档