本論文中，我們提出新的紋理壓縮演算法以及紋理快取的策略。紋理壓縮演算法是利用階層式的調色盤與內插法重建區塊，紋理快取是利用紋理貼圖在提取紋理像素時有區域性以及方向預測向記憶體或系統快取提取紋理資料。以方向預測預先提取該方向的區塊能有效提升快取的命中率。新的紋理壓縮演算法提供更好的影像品質。我們利用內插法取得多個色彩並建立調色盤，提出一個階層化調色盤方法，根據區塊編碼方法分割影像，並以階層化的調色盤編碼更小的區塊，取代單純以像素索引選擇調色盤的色彩。實驗結果證明不論在自然和紋理的測試影像，我們所提出的演算法編碼標準影像資料庫得到的結果平均優於DXT1約2.3dB。使用我們所提出的紋理快取策略相較於未使用此策略有較高的命中率，實驗結果能減少平均15.57%的未命中率。因此，我們提出的方法能有效提升壓縮後的影像品質並提升紋理貼圖系統效能。

To improve the quality of compressed texture, this thesis proposes new texture compression algorithms and a texture cache strategy. We propose a hierarchical palette to increase the color candidates without increasing the index bits. The new texture compression algorithms can provide better image quality. We adopt direction and locality of extracted texel for the texture cache strategy when texture mapping. By predicted direction, the pre-fetch block can effectively improve the cache hit rate. The average gain with our texture compression scheme is better than DXT1 about 2.3 dB PSNR. For the proposed texture cache strategy improves about 15.72% Miss rate.

[1] A. C. Beers, M. Agrawala and N. Chaddha, “Rendering from Compressed Textures,” in Proc. the 23rd annual conference on Computer graphics and interactive techniques, 1996, pp. 373-378.
[2] W. B. Pennebaker and J. L. Mitchell, “JPEG Still Image Data Compression Standard.” Van Nostrand Reinhold, 1993.
[3] L. Ziv and A. Lempel, “A universal algorithm for sequential data compression.” IEEE Trans. Inform.Theory, Vol.IT-23, (3), May 1977.
[4] E. J. Delp and O. R. Mitchell, “Image compression using block truncation coding,” IEEE Trans. Commun., vol. COM-27, pp. 1335-1342, Sep. 1979.
[5] G. Campbell, T. A. DeFanti, J. Frederiksen, S. A. Joyce, L. A. Leske, J. A. Lindberg, and D. J. Sandin, “Two bit/pixel full color encoding,” in Proc. SIGGRAPH 86, 1986, pp. 215-223.
[6] K. I. Iourcha, K. S. Nayak, and Z. Hong, “System and Method for Fixed-Rate Block-Based Image Compression with Inferred Pixel Values,” U.S. Patent 5,956,431, 1999.
[7] S. Fenney, “Texture compression using low-frequency signal modulation,” in Proc. Graphics Hardware 2003, 2003, pp. 84-91.
[8] J. Ström and T. Akenine-Möller, “PACKMAN: Texture compression for mobile phones,” in Sketches Program at SIGGRAPH 04, 2004.
[9] J. Ström and T. Akenine-Möller, “iPACKMAN, high-quality, lowcomplexity texture compression for mobile phones,” in Proc. Graphics Hardware 2005, 2005, pp. 63-70.
[10] J. Ström and M. Pettersson, “ETC2: Texture compression using invalid combinations,” in Proc. Graphics Hardware 2007, 2007, pp. 49-54.
[11] V. Pereberin, “Hierarchical approach for texture compression,” in Proc. GraphiCon99, 1999, pp. 195-199.
[12] J. Stachera, P. Rokita, “Hierarchical texture compression,” in International Conferences in Central Europe on Computer Graphics, Visualization and Computer Vision, pp. 108-120 (1997).
[13] Y. Jian, D. Huan, “Improved texture compression for s3tc,” in Picture Coding Symposium, 2010.
[14] C. H. Sun, Y. M. Tsao, and S. Y. Chien, “High-Quality Mipmapping Texture Compression With Alpha Maps for Graphics Processing Units,” IEEE Trans. on multimedia, 2009, pp. 589-599.
[15] Y. Jiang, M. Gui, D. Lu, Y. Xu, “Texture Compression with Variable Data Formats,” IEEE 12th International Conference on Computer and Information Technology (CIT), 2012.
[16] ATI Technologies. ATI Radeon X800 3Dc White Paper [Online]. Available: http://www.hardwaresecrets.com/datasheets/3Dc White Paper.pdf.
[17] Y. S. Kwon, I. C. Park and C. M. Kyung, “Pyramid texture compression and decompression using interpolative vector quantization,” in Proc. 2000 International Conference on Image Processing, Canada, 2000, vol.2, pp. 191-194.
[18] J. Ström and P. Wennersten., “Table-based Alpha Compression,” EUROGRAPHICS 2009 Computer Graphics Forum, 2009, vol. 28, no. 2, pp. 687-695.
[19] B. Yang and Z. Pan, “A Hybrid Adaptive Normal Map Texture Compression Algorithm,” in ICAT’06. 16th International Conf. Artificial Reality and Telexistence–Workshops, Hangzhou, 2006, pp. 349-354.
[20] P. Kalyuzhny and A. Zhirkov , “Texture compression with adaptive block partitions,” in Proc. MULTIMEDIA ’00 Proc. of the eighth ACM international conference on Multimedia, 2000, pp. 401-403.
[21] 3dfx Interactive, “FXT1 Texture Compression Technology White Paper,” 2000.
[22] J. Nystad and A. Lassen, “Adaptive scalable texture compression,” in Proc. EGGH-HPG’12 Proc. of the Fourth ACM SIGGRAPH /Eurographics conference on High-Performance Graphics, 2012, pp. 105-114.
[23] G. Knittel, A. Schilling,“Hardware for Superior Texture Performance,” in Proc. the Tenth Eurographics conference on Graphics Hardware , 1995, pp. 33-40.
[24] Kodak Lossless True Color Image Suite PhotoCD PCD0992 [Online]. Available: http://r0k.us/graphics/kodak/index.html
[25] ImageProcessingPlace.com. Image Databases [Online]. Available: http://www.imageprocessingplace.com/root files V3/image databases.htm
[26] H. Hanemaaijer texgenpack [Online]. Available: https://github.com/hglm/texgenpack
[27] D. Mullis. (2000, Apr. 12). 3DFX texture compression FXT1 (0.4 ed.) [Online]. Available: http://opengl.org/registry/specs/3DFX/texture_compression_FXT1.txt.
[28] J. Stachera and P. Rokita, ”GPU-Based Hierarchical Texture Decompression,” EUROGRAPHICS, 2006
[29] Z. S. Hakura and A. Gupta, “The design and analysis of a cache architecture for texture mapping,” in Proc. of the 24th annual international symposium on Computer architecture, ser. ISCA ’97. New York, NY, USA: ACM, 1997, pp. 108–120. [Online]. Available: http://doi.acm.org/10.1145/264107.264152
[30] OpenGL ES 2.X. The Standard for Embedded Accelerated 3D Graphics [Online]. Available: https://www.khronos.org/opengles/2_X/
[31] M. Doggett, “Texture Caches,” IEEE Micro, 2012, vol. 32, pp. 136-141
[32] ImageProcessing/VideoCodecs/Programming. Test Still Images. [Online]. Available: http://www.hlevkin.com/default.html#testimages
[33] AMD. HBM. [Online]. Available: http:////www.amd.com/zh-tw/innovations/software-technologies/hbm
[34] L. Williams, “Pyramidal parametrics,” Computer Graphics, New York,1983, vol. 17, no. 3, pp. 1-11