Multi-resolution texture synthesis from turntable image sequences

Abstract

Texture synthesis and texture mapping are important technologies for rendering realistic three-dimensional scene. It has been widely used in virtual reality, urban modeling, 3D animation, gaming and other areas. In this paper, we propose a fast method to construct high quality texture map for multi-resolution texture synthesis from turntable image sequences. Given a 3D mesh model, we first get the projection relationship between 3D mesh and image sequences. We then use image sequences to construct a texture triangle for each 3D triangle mesh and get a global rectangular texture map for the whole mesh. Another approach to construct a texture map is using Stretch-minimizing mesh parameterization. Finally, we map the texture to mesh model to verify the quality of these two methods. The high performance of this method has been demonstrated in many real object models.

Keywords

texture synthesis / multi-resolution / texture map / texture mapping

References

[1] Blinn J F, Newell M E. Texture and reflection in computer generated images. Communications of the ACM, 1976, 19(10): 542–547

[2] Catmull E. Subdivision algorithm for computer display of curved surface. Dissertation for the Doctoral Degree. University of Utah, 1974

[3] Perlin K. An image synthesizer. Proceedings of the 12^th Annual Conference on Computer Graphics and Interactive Techniques, 1985, 19(3): 287–296

[4] Peachey D R. Solid texturing of complex surfaces. In: Proceedings of the 12th Annual Conference on Computer Graphics and Interactive Techniques, 1985, 19(3): 279–286.

[5] Worley S. A cellular texture basis function. Proceedings of the 23^rd Annual Conference on Computer Graphics and Interactive Techniques, 1996, 19(4):291–294.

[6] Soucy M, Laurendeau D. A dynamic integration algorithm to model surfaces from multiple range views. Machine Vision and Applications, 1995, 8(1): 53–62

[7] Soucy M, Laurendeau D. A general surface approach to the integration of a set of range views. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(4): 344–358

[8] Alexei A. Efros &William T. Freeman. Image quilting for texture synthesis and transfer. In: Proceedings of the 28th Annual Conference on Computer graphics and interactive techniques, Los Angeles, California, 2001, 341–347

[9] Song P, Wu X J, Wang M Y. Multi-view stereo reconstruction for 3D object. In: Proceedings of the IEEE International Conference on Robotics and Automation, Zhuhai, 2009, 784–789

[10] Song P, Wu X J, Wang M Y. Multi-view stereo reconstruction with silhouette constraint. The Visual Computer, 2010, 26(12): 1435–1450

[11] Soucy M, Godin G, Rioux M. A texture mapping approach for the compression of colored 3D triangulations. Visual Computer, 1996, 12(10): 503–514

[12] Esteban C H. Stereo and silhouette fusion for 3D object modeling from uncalibrated images under circular motion. Dissertation for the Doctoral Degree, ENST, 2004

[13] Bighead sequence. http://www.tsi.enst.fr/3dmodels/html/enst/bigHead.html

[14] Yoshizawa S, Belyaev A, Seidel H P. A fast and simple stretch-minimizing mesh parameterization. Shape Modeling Applications, 2004, Proceedings, 200–208

Acknowledgements

This project is partially supported by the National Natural Science Foundation of China (Grant No. 61063019), Science & Technology Basic Research Projects of Shenzhen (Nos. JC200903120184A and JC201005260161A), and Foundation of the State Key Laboratory of Digital Manufacturing Equipment & Technology (No. DMETKF2009013), Science & Technology Foundation of Nanshan, Shenzhen (No. 201002).

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg