Emulating the human interpretation of line-drawings as three-dimensional objects
International Journal of Computer Vision
An optimization-based approach to the interpretation of single line drawings as 3D wire frames
International Journal of Computer Vision
The HoloSketch VR sketching system
Communications of the ACM
3D Shape Reconstruction by Using Vanishing Points
IEEE Transactions on Pattern Analysis and Machine Intelligence
SKETCH: an interface for sketching 3D scenes
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
An interface for sketching 3D curves
I3D '99 Proceedings of the 1999 symposium on Interactive 3D graphics
Teddy: a sketching interface for 3D freeform design
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Interactive 3D modeling using only one image
VRST '00 Proceedings of the ACM symposium on Virtual reality software and technology
Annotating and sketching on 3D web models
Proceedings of the 7th international conference on Intelligent user interfaces
Sketching annotations in a 3D web environment
CHI '02 Extended Abstracts on Human Factors in Computing Systems
Pen-based styling design of 3D geometry using concept sketches and template models
Proceedings of the 2006 ACM symposium on Solid and physical modeling
A survey of sketch-based 3-D modeling techniques
Interacting with Computers
Design Framework for Sketch Based Technique in 3D Navigation of Cluttered Virtual Environment
IVIC '09 Proceedings of the 1st International Visual Informatics Conference on Visual Informatics: Bridging Research and Practice
Hi-index | 0.00 |
Here we demonstrate the direct input to computer of a handdrawn perspective sketch to create a virtual environment. We either start with a photograph of a real environment or an existing VRML model, and then use a mouse or pen pad to sketch line drawings onto the scene. Visual clues and constraints from the existing background and line drawing, as well as heuristics for form recognition are used to build a 3D optimization problem. We use a multiple objective genetic algorithm to find a viable solution to the problem, and VRML output is generated, either for re-entry to the system or use in another system. Our software is currently available compiled for either a PC running Windows 98/NT or an SGI machine running IRIX 6.x.