- 3D Object Manipulation in a Single Photograph using Stock 3D Models
Arthur
Natasha Kholgade,Tomas Simon,Alexei Efros,Yaser Sheikh
Abstract
Photo-editing software restricts the control of objects in a photograph to the 2D image plane. We present a method that enables users to perform the full range of 3D manipulations, including scaling, rotation, translation, and nonrigid deformations, to an object in a photograph. As 3D manipulations often reveal parts of the object that are hidden in the original photograph, our approach uses publicly available 3D models to guide the completion of the geometry and appearance of the revealed areas of the object. The completion process leverages the structure and symmetry in the stock 3D model to factor out the effects of illumination, and to complete the appearance of the object. We demonstrate our system by producing object manipulations that would be impossible in traditional 2D photo-editing programs, such as turning a car over, making a paper-crane flap its wings, or manipulating airplanes in a historical photograph to change its story.
Publication
ACM Transaction on Graghics. July 2014.
https://doi.org/10.1145/2601097.2601209
以上期刊心得 :
1.在照片上直觀執行3D操作，無需訪問原始場景或拍攝照片的時刻。使用者可以方便地創建定格動畫來克服物理限制。此研究方法也可將其用於校正公共資料庫中3D模型的幾何形狀和外觀。
2.該研究方法的基本局限性在於採樣，如果拍攝對象的影像尺寸空間很小，可能會缺少像素樣本，在這種情況下，可能會產生模糊的結果。
3.如果3D資料庫中的模型設計不正確或設計太粗糙，可能會發生問題，尤其是在物件具有複雜幾何形狀和小零件繁瑣的情況下。
4.個人發現3D重建(3D RECONSTRUCTION)的學術研究或技術開發最大的課題還是在解決造型與光影於人類視覺經驗中的可視性問題與合理呈現問題，這也是要不斷去克服與創新的電腦科學工程。
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
2 . TeeVR: spatial template-based acquisition, modeling, and rendering of large-scale indoor spaces
Arthur
Nathan Doh, Hyunga Choi, Bumchul Jang, Sangmin, Hyojin Jung, Sungkil Lee.
Abstract
Conventional image-based rendering has limited applicability for large-scale spaces. In this study, we demonstrate an efficient alternative to conventional image-based rendering. Our key approach is based on a spatial template (ST), which solely includes architectural geometric primitives. The predictability of ST improves the efficiency of acquisition, storage, and rendering. Thereby, our system can be applied to the modeling and rendering of larger indoor spaces.
Publication
ACM SIGGRAPH 2019 Emerging Technologies
July 2019 Article No.25 pp1-1
https://doi.org/10.1145/3305367.3327989
以上期刊心得
1.對於快速建立大型室內空間的模型生成，確實有很大的自動化生成成果，尤其該研究可以精準測距，提供正確的空間的尺度與比例。對於建築設計、室內設計、室內照明設計能夠提供很大的幫助。當然，此研究技術開發對於運用在電腦遊戲模擬真實世界的實際場景的建立也是非常好的場景快速生成方法。
2.很可惜的是在場景中的建立是針對所謂該研究的Spatial Template 也有就是空間中的天、地、牆板、梁柱的基本元素建立，空間中的裝置、擺設等等因運算處理速度關係，於本研究中全部去除不計考量，而場景中的許多立面畫面皆以攝影鏡頭捕捉後直接用Mapping方式，故空間中的立面層次與立體感皆扁平化而失真，較為可惜。當然，這也是值得研究下去的另一個開發課題。
