Interpreting line drawings of curved objects
Interpreting line drawings of curved objects
Numerical recipes in C: the art of scientific computing
Numerical recipes in C: the art of scientific computing
Modeling and rendering architecture from photographs: a hybrid geometry- and image-based approach
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
SKETCH: an interface for sketching 3D scenes
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Tour into the picture: using a spidery mesh interface to make animation from a single image
Proceedings of the 24th annual conference on Computer graphics and interactive techniques
Multiple view geometry in computer visiond
Multiple view geometry in computer visiond
Image-based modeling and photo editing
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
A suggestive interface for 3D drawing
Proceedings of the 14th annual ACM symposium on User interface software and technology
ACM SIGGRAPH 2005 Papers
3D screen-space widgets for non-linear projection
GRAPHITE '05 Proceedings of the 3rd international conference on Computer graphics and interactive techniques in Australasia and South East Asia
On expert performance in 3D curve-drawing tasks
Proceedings of the 6th Eurographics Symposium on Sketch-Based Interfaces and Modeling
Analytic drawing of 3D scaffolds
ACM SIGGRAPH Asia 2009 papers
ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
Stereoscopizing cel animations
ACM Transactions on Graphics (TOG)
Depth sculpturing for 2D paintings: A progressive depth map completion framework
Journal of Visual Communication and Image Representation
Hi-index | 0.00 |
We present a semi-automatic framework for construction of curved and polygonal 3D models from a 2D line drawing, such as architectural or mechanical drawings. Despite advances in image-based modeling, 3D modeling from a drawn image remains largely manual. In contrast, our method only requires the user to annotate the source image with a drawn cube for camera calibration. 3D models are then generated automatically. The modeling process has four steps: camera calibration, a novel line detection algorithm for noisy input, line labeling to calculate polygon adjacencies, a new incremental construction method that uses plane hinging-angle optimization to improve scalability over previous approaches. We also present algorithms for handling curved surfaces when they are part of a polygonal model that provides boundary conditions.