Authors:
Jinxin Zheng
;
Yongtao Wang
and
Zhi Tang
Affiliation:
Peking University, China
Keyword(s):
3D Reconstruction, Line Drawing, Sketch Extraction.
Related
Ontology
Subjects/Areas/Topics:
CAGD/CAD/CAM Systems
;
Computer Vision, Visualization and Computer Graphics
;
Geometry and Modeling
;
Integration and Interoperation Between 3D Documents and Web/Multimedia Technologies, Including the Semantic Web
;
Interactive 3D Graphics for Mobile Devices Like Smartphones, PDAs and UMPCs
;
Interactive Environments
Abstract:
We present a robust method to reconstruct solid geometric object from single line drawing image taken from the geometric books. Unlike most of the existing methods which require perfect and complete sketches of the line drawings as the inputs, our method directly takes the line drawing images as the inputs and can well handle the incomplete sketches that are automatically produced by our sketch extraction algorithm. The proposed method consists of three major steps as follows: First, the sketch of the input line drawing (i.e., line segments and their intersections) is automatically extracted and further represented as an undirected graph. Second, candidate 3D models from the pre-built 3D model database are found by graph matching. Third, for each candidate 3D model, the model parameters, the rotation and the translation aligning the model with the sketch, are found by optimizing an objective function which is composed of the residuals between the vertices of the sketch and the 2D pro
jections of the candidate model’s vertices, and an optimal reconstruction solution is further selected as the final result. Experimental results show that our method can effectively reconstruct the solid geometric object from single line drawing image.
(More)