Content Aware Texture Compression

Efficient and high quality texture compression is important because computational powers are always limited, especially for embedded systems such as mobile phones. To access random texels instantly, down sampling and S3TC are the most commonly used methods due to the fixed compression ratio at every local region. However, the methods are content oblivious, which uniformly discard texel information. Therefore, we present content aware warp to reduce a texture resolution, where homogeneous regions are squeezed more to retain more structural information. We then relocate texture coordinates of the 3D model as the way of relocating texels, such that rendering the model with our compressed texture requires no additional decompression cost. Our texture compression technique can cooperate with existing methods such as S3TC since the compression strategies are independent. By reducing texture resolution in a content aware manner, followed by texture compression using S3TC, as the experiments show, we achieve higher compression ratios without degrading visual quality significantly.

[1]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[2]  Martin Pettersson,et al.  ETC2: texture compression using invalid combinations , 2007, GH '07.

[3]  Tomas Akenine-Möller,et al.  PACKMAN: texture compression for mobile phones , 2004, SIGGRAPH '04.

[4]  Pedro V. Sander,et al.  Signal-Specialized Parametrization , 2002, Rendering Techniques.

[5]  Pedro V. Sander,et al.  Signal-specialized parameterization for piecewise linear reconstruction , 2004, SGP '04.

[6]  Daniel Cohen-Or,et al.  Non-homogeneous Content-driven Video-retargeting , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[7]  O. Sorkine,et al.  Optimized scale-and-stretch for image resizing , 2008, SIGGRAPH 2008.

[8]  Wolfgang Straßer,et al.  Hardware for Superior Texture Performance , 1995, Workshop on Graphics Hardware.

[9]  A. Ramesh Babu,et al.  A generic approach for nesting of 2-D parts in 2-D sheets using genetic and heuristic algorithms , 2001, Comput. Aided Des..

[10]  ShamirAriel,et al.  Improved seam carving for video retargeting , 2008 .

[11]  Stefano Soatto,et al.  Texture Compression , 2013, 2013 Data Compression Conference.

[12]  Truong Q. Nguyen,et al.  Selective Data Pruning-Based Compression Using High-Order Edge-Directed Interpolation , 2009, IEEE Transactions on Image Processing.

[13]  Tomas Akenine-Möller,et al.  iPACKMAN: high-quality, low-complexity texture compression for mobile phones , 2005, HWWS '05.

[14]  Julia A. Bennell,et al.  The geometry of nesting problems: A tutorial , 2008, Eur. J. Oper. Res..

[15]  Daniel Cohen-Or,et al.  Feature-aware texturing , 2006, EGSR '06.

[16]  Olga Sorkine-Hornung,et al.  Visual media retargeting , 2009, SIGGRAPH ASIA Courses.

[17]  Thomas A. DeFanti,et al.  Two bit/pixel full color encoding , 1986, SIGGRAPH.

[18]  Ariel Shamir,et al.  Improved seam carving for video retargeting , 2008, SIGGRAPH 2008.

[19]  S. Avidan,et al.  Seam carving for content-aware image resizing , 2007, SIGGRAPH 2007.

[20]  John M. Snyder,et al.  Signal-Specialized Parameterization , 2002 .