“Vector-Regression Functions for Texture Compression” by Wang, Song, Wei and Wang

  • ©Jiaping Wang, Ying Song, LiYi Wei, and Wencheng Wang

Conference:


Type:


Title:

    Vector-Regression Functions for Texture Compression

Session/Category Title: TEXTURE


Presenter(s)/Author(s):


Moderator(s):



Abstract:


    Raster images are the standard format for texture mapping, but they suffer from limited resolution. Vector graphics are resolution-independent but are less general and more difficult to implement on a GPU. We propose a hybrid representation called vector regression functions (VRFs), which compactly approximate any point-sampled image and support GPU texture mapping, including random access and filtering operations. Unlike standard GPU texture compression, (VRFs) provide a variable-rate encoding in which piecewise smooth regions compress to the square root of the original size. Our key idea is to represent images using the multilayer perceptron, allowing general encoding via regression and efficient decoding via a simple GPU pixel shader. We also propose a content-aware spatial partitioning scheme to reduce the complexity of the neural network model. We demonstrate benefits of our method including its quality, size, and runtime speed.

References:


    1. S. Boyé, P. Barla, and G. Guennebaud. 2012. A vectorial solver for free-form vector gradients. ACM Trans. Graph. 31, 6 (Nov.), 173:1–173:9. 
    2. C. Dachsbacher. 2011. Analyzing visibility configurations. IEEE Trans. Visual. Comput. Graph. 17, 4 (Apr.), 475–486. 
    3. C. Dong, C. C. Loy, K. He, and X. Tang. 2015. Image super-resolution using deep convolutional networks. CoRR abs/1501.00092.
    4. R. Fattal. 2007. Image upsampling via imposed edge statistics. In Proceedings of the ACM SIGGRAPH Papers (SIGGRAPH’07). ACM, New York, NY. 
    5. M. Finch, J. Snyder, and H. Hoppe. 2011. Freeform vector graphics with controlled thin-plate splines. In Proceedings of the SIGGRAPH Asia Conference (SA’11). ACM, New York, NY, 166:1–166:10. 
    6. R. Franzen. 1999. Kodak lossless true color image suite. http://r0k.us/graphics/kodak/.
    7. F. Ganacim, R. S. Lima, L. H. de Figueiredo, and D. Nehab. 2014. Massively-parallel vector graphics. ACM Trans. Graph. 33, 6 (Nov.), 229:1–229:14. 
    8. R. Grzeszczuk, D. Terzopoulos, and G. Hinton. 1998. Neuroanimator: Fast neural network emulation and control of physics-based models. In Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’98). 9–20. 
    9. M. T. Hagan and M. B. Menhaj. 1994. Training feedforward networks with the Marquardt algorithm. Trans. Neur. Netw. 5, 6 (Nov.), 989–993. 
    10. P. S. Heckbert. 1986. Survey of texture mapping. IEEE Comput. Graph. Appl. 6, 11 (Nov.), 56–67. 
    11. G. E. Hinton. 1989. Connectionist learning procedures. Artif. Intell. 40, 1–3 (Sept.), 185–234. 
    12. P. Ilbery, L. Kendall, C. Concolato, and M. McCosker. 2013. Biharmonic diffusion curve images from boundary elements. ACM Trans. Graph. 32, 6 (Nov.), 219:1–219:12. 
    13. K. Iourcha, K. Nayak, and Z. Hong. 1999. System and method for fixed-rate block-based image compression with inferred pixel values. U.S. Patent 5956431, filed October 2, 1997, and issued September 21, 1999.
    14. S. Jeschke, D. Cline, and P. Wonka. 2009. Rendering surface details with diffusion curves. In Proceedings of the ACM SIGGRAPH Asia Papers (SIGGRAPH Asia’09). 117:1–117:8. 
    15. J. Jiang. 1999. Image compression with neural networks –A survey. Signal Process. Image Commun. 14, 9 (July), 737–760.
    16. Y.-K. Lai, S.-M. Hu, and R. R. Martin. 2009. Automatic and topology-preserving gradient mesh generation for image vectorization. In Proceedings of the ACM SIGGRAPH Papers (SIGGRAPH’09). ACM, New York, NY, 85:1–85:8. 
    17. G. Lecot and B. Levy. 2006. Ardeco: Automatic region detection and conversion. In Proceedings of the 17th Eurographics Conference on Rendering Techniques (EGSR’06). Eurographics Association, Aire-la-Ville, Switzerland, 349–360. 
    18. S. Lefebvre and H. Hoppe. 2005. Parallel controllable texture synthesis. In Proceedings of the ACM SIGGRAPH Papers (SIGGRAPH’05). 777–786. 
    19. S. Lefebvre and H. Hoppe. 2006. Perfect spatial hashing. In Proceedings of the ACM SIGGRAPH Papers (SIGGRAPH’06). ACM, New York, NY, 579–588. 
    20. P. Mavridis and G. Papaioannou. 2011. High quality elliptical texture filtering on GPU. In Proceedings of the Symposium on Interactive 3D Graphics and Games (I3D’11). 23–30. 
    21. J. McCormack, R. Perry, K. I. Farkas, and N. P. Jouppi. 1999. Feline: Fast elliptical lines for anisotropic texture mapping. In Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’99). 243–250. 
    22. Microsoft Corporation. 2013. Directx11 bc6h/bc7 directcompute encoder tool. https://code.msdn.microsoft.com/windowsdesktop/BC6HBC7-DirectCompute-35e8884a.
    23. D. Nehab and H. Hoppe. 2008. Random-access rendering of general vector graphics. ACM Trans. Graph. 27, 5 (Dec.), 135:1–135:10. 
    24. D. Nowrouzezahrai, E. Kalogerakis, and E. Fiume. 2009. Shadowing dynamic scenes with arbitrary brdfs. Comput. Graph. Forum 28, 2, 249–258.
    25. J. Nystad, A. Lassen, A. Pomianowski, S. Ellis, and T. Olson. 2012. Adaptive scalable texture compression. In Proceedings of the 4th ACM SIGGRAPH/Eurographics Conference on High-Performance Graphics (EGGH-HPG’12). Eurographics Association, Aire-la-Ville, Switzerland, 105–114. 
    26. M. Olano, D. Baker, W. Griffin, and J. Barczak. 2011. Variable bit rate GPU texture decompression. In Proceedings of the 22nd Eurographics Conference on Rendering (EGSR’11). 1299–1308. 
    27. Opengl Arb. 2010. Arb texture compression bptc. http://www.opengl.org/registry/specs/ARB/texture_compression_bptc.txt.
    28. A. Orzan, A. Bousseau, H. Winnemöller, P. Barla, J. Thollot, and D. Salesin. 2008. Diffusion curves: A vector representation for smooth-shaded images. In Proceedings of the ACM SIGGRAPH Papers (SIGGRAPH’08). ACM, New York, NY, 92:1–92:8. 
    29. E. Parilov and D. Zorin. 2008. Real-time rendering of textures with feature curves. ACM Trans. Graph. 27, 1 (Mar.), 3:1–3:15. 
    30. Z. Qin, M. D. McCool, and C. Kaplan. 2008. Precise vector textures for real-time 3D rendering. In Proceedings of the Symposium on Interactive 3D Graphics and Games (I3D’08). 199–206. 
    31. P. Ren, J. Wang, M. Gong, S. Lin, X. Tong, and B. Guo. 2013. Global illumination with radiance regression functions. ACM Trans. Graph. 32, 4 (July), 130:1–130:12. 
    32. P. Sen. 2004. Silhouette maps for improved texture magnification. In Proceedings of the ACM SIGGRAPH/EUROGRAPHICS Conference on Graphics Hardware (HWWS’04). 65–73. 
    33. Q. Shan, Z. Li, J. Jia, and C.-K. Tang. 2008. Fast image/video upsampling. In Proceedings of the ACM SIGGRAPH Asia Papers (SIGGRAPH Asia’08). 153:1–153:7. 
    34. J. Ström and T. Akenine-Möller. 2005. ipackman: High-quality, low-complexity texture compression for mobile phones. In Proceedings of the ACM SIGGRAPH/EUROGRAPHICS Conference on Graphics Hardware (HWWS’05). ACM, New York, NY, 63–70. 
    35. J. Sun, L. Liang, F. Wen, and H.-Y. Shum. 2007. Vectorization using optimized gradient meshes. In Proceedings of the ACM SIGGRAPH Papers (SIGGRAPH’07). ACM, New York, NY. 
    36. T. Sun, P. Thamjaroenporn, and C. Zheng. 2014. Fast multipole representation of diffusion curves and points. ACM Trans. Graph. 33, 4 (July), 53:1–53:12. 
    37. X. Sun, G. Xie, Y. Dong, S. Lin, W. Xu, W. Wang, X. Tong, and B. Guo. 2012. Diffusion curve textures for resolution independent texture mapping. ACM Trans. Graph. 31, 4 (July), 74:1–74:9. 
    38. M. Tarini and P. Cignoni. 2005. Pinchmaps: Textures with customizable discontinuities. Comput. Graph. Forum 24, 3, 557–568.
    39. J. Tumblin and P. Choudhury. 2004. Bixels: Picture samples with sharp embedded boundaries. In Proceedings of the 15th Eurographics Conference on Rendering Techniques (EGSR’04). 255–264. 
    40. V. N. Vapnik. 1995. The Nature of Statistical Learning Theory. Chapter IV. Springer-Verlag New York, Inc., New York, NY. 
    41. L. Williams. 1983. Pyramidal parametrics. In Proceedings of the 10th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’83). 1–11. 
    42. T. Xia, B. Liao, and Y. Yu. 2009. Patch-based image vectorization with automatic curvilinear feature alignment. In Proceedings of the ACM SIGGRAPH Asia Papers (SIGGRAPH Asia’09). ACM, New York, NY, 115:1–115:10. 
    43. G. Xie, X. Sun, X. Tong, and D. Nowrouzezahrai. 2014. Hierarchical diffusion curves for accurate automatic image vectorization. ACM Trans. Graph. 33, 6 (Nov.), 230:1–230:11.

ACM Digital Library Publication:



Overview Page: