Full metadata record
DC FieldValueLanguage
dc.contributor.author陳威丞en_US
dc.contributor.authorChen, Wei-Chengen_US
dc.contributor.author林奕成en_US
dc.contributor.authorLin, I-Chenen_US
dc.date.accessioned2014-12-12T02:37:30Z-
dc.date.available2014-12-12T02:37:30Z-
dc.date.issued2013en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#GT070056640en_US
dc.identifier.urihttp://hdl.handle.net/11536/73280-
dc.description.abstract利用單一視角的資訊來重建我們想要的模型是一件具有挑戰性的事情。此外,由於深度掃描資訊是一個不完整並且包含許多雜訊的資料,我們利用從同一個角度所拍攝的彩色圖片來提供更多的線索幫助重建工作。由於現實生活中的物體不斷的在增加,如果只用現有的3D模型去做變形是不夠的。在這篇論文當中,我們提出了一個part-assembly的方法來重建這些結構。首先,我們會從模型資料庫之中找出一個跟我們想要重建的物體最相像的模型,利用這個模型來幫助下一個步驟做對齊。利用這個最相像的模型自己的座標系統找出跟我們想重建的模型之間的轉換來達到將所有資料庫中的模型對齊的效果。最後,我們從資料庫的模型中找出跟想重建的模型每個部分最相像的部分,並且對這些部分做變形來符合輸入的資料,並且重組這些部分合成完就是我們想要的模型。zh_TW
dc.description.abstractIt is challenging to reconstruct the target object from monocular view because of the limitation of the input data. Otherwise, since range scan is an incomplete and noisy data, we incorporate the color image captured from the same viewpoint to provide extra cues. Because of the growing popularity of real world objects, it is not enough to reconstruct the target object only by deforming the existing models. In this thesis, we propose a part-assembly approach to reconstruct the structure. First, we retrieve the most similar model, which is called representative model from database to guide the model alignment. With the representative model, we use the primary facet axes between the point cloud and the model to align all the database models. Finally, we deform the most similar part retrieved from database to fit the target object and compose them to reconstruct the final structure we want.en_US
dc.language.isozh_TWen_US
dc.subject部分組合zh_TW
dc.subject代表模型zh_TW
dc.subject模型座標系統zh_TW
dc.subjectPart-assembly approachen_US
dc.subjectrepresentative modelen_US
dc.subjectprimary facet axesen_US
dc.title從單一視角利用局部物件標識及組合重建模型zh_TW
dc.titleObject Reconstruction Using Part Labeling and Composition from Monocular Viewen_US
dc.typeThesisen_US
dc.contributor.department多媒體工程研究所zh_TW
Appears in Collections:Thesis