線條藝術 (Wire art) 是一種使用金屬線作為素材的藝術創作, 藝術家們會在單一線條裝置藝術中透過結合不同的視角, 讓觀看者能從不同的角度辨識出截然不同的 2D 影像, 這樣一種特殊且令人驚豔的藝術創作我們稱之為”多重視角成像之線條藝術 (multi-view wire art)”. 專業的藝術家可以藉由受過訓練的藝術能力來創作出這樣一種作品, 但在創作上所花費的時間是相當可觀的, 而對一般人來說, 要創作這一樣一個多重視角之線條藝術是相當有難度的. 因此我們設計了一個計算工具, 使用者輸入一組 2D 的線條繪畫, 數量通常為 2 或 3 張, 以及相對應的視角和視線設定, 系統會輸出一個由 3D 曲線所構成的模型, 從特定視角觀看可以觀察到模型的投影是跟輸入的線條繪畫是相似的. 在使用者提供輸入之後, 我們會先在離散的 3D 空間中尋找一個體素的集合, 該集合滿足在投影之後能夠完整覆蓋 2D 的線條繪畫且最小化投影過後覆蓋到背景的部分, 以維持投影過後的相似性. 為了實現最後 輸出的結構能夠在現實世界中被製造並且展示, 我們會使用”有限制的 3D 尋路演算法”將由此體素集合形成的結構轉變成一個單一的聯通單元, 然後再使用 volumetric thinning 的演算法計算該 3D 結構的骨架, 由此我們得到了一個由 3D 曲線構成的結構, 且該結構維持 單一連通單元的特性. 在最後我們會減少構成結構的曲線數量來簡化結構, 注意結構在簡化 之後仍然可以在投影之後維持與 2D 線條繪畫的相似性, 再透過變形讓購成結構的線條能夠更加平滑且能夠更加逼近 2D 線條繪畫. 我們在這篇研究中展示了使用不同數量的輸入 線條繪畫, 其中有不同的圖形複雜度, 和不同的視角設定所計算出來的多重視角成像之線條藝術, 且透過電腦繪圖成像和使用 3D 列印機列印並實際展示的方式來說明我們的系統是有能力可以創造這樣一種特殊的裝置藝術

Wire art is a unique art form that making sculpture with metal wire. Some of the professional artist would combine various viewing angel so that observer can recognize the different 2D line drawing from the sculpture, and the line drawings are potentially very different. We call this interesting and amazing art work “Multi-view wire art”. A professional artist is capable of creating this kind of the sculpture, but it would take so mesh time and efforts to creating and designing. For novice user it is hardly to have a multi-view wire art by themself. So we present a computation tool that the input is a set of 2D line drawings and associated viewing configurations, and the system would output a 3D object which is composed of 3D curves, user is able to observe the 2d projection similar to the input line drawings of the sculpture from specify viewpoint. Our computation process consist of four steps, first is we find a voxel set from the discrete volume and make sure that the projection of the voxel set can completely cover the line pixels of whole input line drawings and minimize the part of projection to the background. For the physically realizable, we form a voxel set a single connected component with“constrained 3D pathfinding”algorithm. We apply the“volumetric thinning”approach to the sculpture to obtain a curve set. Then we simplify the curve structure by reduce the number of curves and keep the completeness of the projection and deform the structure for smoothness and shape approximation. We demonstrate the effectiveness of our system with the results created from different viewing configurations and line drawing complexity and exhibit these multi-view wire art both in simulation and 3D physical world.

Noah Snavely, Steven M Seitz, and Richard Szeliski. Photo tourism: exploring photo collections in 3d. In ACM Trans. Graph. (Proc. of SIGGRAPH) , volume 25, pages 835–846,2006.

Johannes L Schonberger and Jan-Michael Frahm. Structure-from-motion revisited. In CVPR, 2016.

Yasutaka Furukawa and Jean Ponce. Accurate, dense, and robust multiview stereopsis. IEEE Trans. Pattern Analysis Machine Intelligence, 32(8):1362–1376, 2010.

Michael Goesele, Noah Snavely, Brian Curless, Hugues Hoppe, and Steven M Seitz. Multi-view stereo for community photo collections. In ICCV, 2007.

Po-Han Huang, Kevin Matzen, Johannes Kopf, Narendra Ahuja, and Jia-Bin Huang. Deep-mvs: Learning multi-view stereopsis. In CVPR, 2018.

Johannes L Schönberger, Enliang Zheng, Jan-Michael Frahm, and Marc Pollefeys. Pixelwise view selection for unstructured multi-view stereo. In ECCV, 2016.

Andreas Kuhn, Heiko Hirschmüller, Daniel Scharstein, and Helmut Mayer. A tv prior for high-quality scalable multi-view stereo reconstruction. International Journal of Computer Vision, 124(1):2–17, 2017.

Yasutaka Furukawa and Carlos Hernández. Multi-view stereo: A tutorial.Foundations and Trends® in Computer Graphics and Vision, 9(1-2):1–148, 2015.

Manuel Hofer, Michael Maurer, and Horst Bischof. Efficient 3d scene abstraction using line segments. Computer Vision and Image Understanding, 157:167–178, 2017.

Ricardo Fabbri and Benjamin Kimia. 3d curve sketch: Flexible curve-based stereo reconstruction and calibration. In CVPR, 2010.

Anil Usumezbas, Ricardo Fabbri, and Benjamin B Kimia. From multiview image curves to 3d drawings. In ECCV, 2016

Lingjie Liu, Duygu Ceylan, Cheng Lin, Wenping Wang, and Niloy J. Mitra. Image-based reconstruction of wire art. ACM Trans. Graph. (Proc. of SIGGRAPH), 36(4):63:1–63:11, 2017.

Richard Szeliski. Rapid octree construction from image sequences. CVGIP: Image under-standing, 58(1):23–32, 1993.

A. Laurentini. The visual hull concept for silhouette-based image understanding. IEEE Trans. Pattern Analysis Machine Intelligence, 16(2):150–162, 1994.

Wojciech Matusik, Chris Buehler, Ramesh Raskar, Steven J Gortler, and Leonard McMil-lan. Image-based visual hulls. In Proc. of ACM SIGGRAPH, 2000.

Svetlana Lazebnik, Yasutaka Furukawa, and Jean Ponce. Projective visual hulls. International Journal of Computer Vision, 74(2):137–165, 2007.

Alec Rivers, Frédo Durand, and Takeo Igarashi. 3d modeling with silhouettes. ACM Trans. Graph. (Proc. of SIGGRAPH), 29(4):109:1–109:8, 2010. ISSN 0730-0301.

Luke Olsen, Faramarz F Samavati, Mario Costa Sousa, and Joaquim A Jorge. Sketch-based modeling: A survey. Computers & Graphics, 33(1):85–103, 2009.

Aude Oliva, Antonio Torralba, and Philippe G. Schyns. Hybrid images. ACM Trans. Graph. (Proc. of SIGGRAPH), 25(3):527–532, 2006.

Ying-Miao Kuo, Hung-Kuo Chu, Ming-Te Chi, Ruen-Rone Lee, and Tong-Yee Lee. Generating ambiguous figure-ground images. IEEE Trans. Vis. Comput. Graph., PP, 2016.

Marc Alexa and Wojciech Matusik. Reliefs as images. ACM Trans. Graph. (Proc. Of SIGGRAPH), 29(4):60–1, 2010.

Amit Bermano, Ilya Baran, Marc Alexa, and Wojciech Matusk. Shadowpix: Multiple images from self shadowing. In Comput. Graph. Forum (Proc. EUROGRAPHICS), volume 31, pages 593–602, 2012.

Guy Sela and Gershon Elber. Generation of view dependent models using free form deformation. The Visual Computer, 23(3):219–229, 2007.

Jeroen Keiren, Freek van Walderveen, and Alexander Wolff. Constructability of trip-lets. In 25th European Workshop on Comp. Geom. 2009.

Niloy J. Mitra and Mark Pauly. Shadow art. ACM Trans. Graph. (Proc. of SIGGRAPH Asia) , 28(5):156:1–156:7, 2009.

Sehee Min, Jaedong Lee, Jungdam Won, and Jehee Lee. Soft shadow art. In Proc. of the Symposium on Computational Aesthetics, page 3, 2017.

Jungdam Won and Jehee Lee. Shadow theatre: discovering human motion from a sequence of silhouettes. ACM Trans. Graph. (Proc. of SIGGRAPH), 35(4):147, 2016.

Emmanuel Iarussi, Wilmot Li, and Adrien Bousseau. Wrapit: computer-assisted crafting of wire wrapped jewelry. ACM Trans. Graph. (Proc. of SIGGRAPH Asia), 34(6):221, 2015.

Eder Miguel, Mathias Lepoutre, and Bernd Bickel. Computational design of stable planarrod structures. ACM Trans. Graph. (Proc. of SIGGRAPH), 35(4):86:1–86:11, 2016.

Jonas Zehnder, Stelian Coros, and Bernhard Thomaszewski. Designing structurally-sound ornamental curve networks. ACM Trans. Graph. (Proc. of SIGGRAPH), 35(4):99:1–99:10,
2016