Currently, the use of the 2D wavelet transform in texture compression for real-time texture mapping on the GPU is limited. The main cause of this is the lack of real-time texture filtering implementations which do not require specialized hardware. This work proposes a novel system to perform 2D wavelet reconstruction and bilinear texture filtering using a high performance GPU shader. The system is able to generate a performant GLSL shader for arbitrary wavelet filter configurations. This goes beyond earlier works in the literature proposing Haar wavelet and Discrete Cosine Transform (DCT) implementations on the GPU. We analyse the shader performance and run-time complexity for several wavelet filters. The experimental results show that filters longer than Haar are deployable on the GPU while maintaining accurate texture filtering and real-time performance.
Andries, B, Munteanu, A, Lemeire, J & Schelkens, P 2013, Real-time texture sampling and reconstruction with wavelet filters. in Multimedia Signal Processing (MMSP). IEEE, pp. 328-332, Multimedia Signal Processing (MMSP), 2013 IEEE 15th International Workshop on, Pula, Croatia, 30/09/13.
Andries, B., Munteanu, A., Lemeire, J., & Schelkens, P. (2013). Real-time texture sampling and reconstruction with wavelet filters. In Multimedia Signal Processing (MMSP) (pp. 328-332). IEEE.
@inproceedings{41deae375bd14ba08d006f9742adc3ef,
title = "Real-time texture sampling and reconstruction with wavelet filters",
abstract = "Currently, the use of the 2D wavelet transform in texture compression for real-time texture mapping on the GPU is limited. The main cause of this is the lack of real-time texture filtering implementations which do not require specialized hardware. This work proposes a novel system to perform 2D wavelet reconstruction and bilinear texture filtering using a high performance GPU shader. The system is able to generate a performant GLSL shader for arbitrary wavelet filter configurations. This goes beyond earlier works in the literature proposing Haar wavelet and Discrete Cosine Transform (DCT) implementations on the GPU. We analyse the shader performance and run-time complexity for several wavelet filters. The experimental results show that filters longer than Haar are deployable on the GPU while maintaining accurate texture filtering and real-time performance.",
keywords = "GPU, wavelet, parallel, transform",
author = "Bob Andries and Adrian Munteanu and Jan Lemeire and Peter Schelkens",
year = "2013",
month = sep,
day = "30",
language = "English",
isbn = "978-1-4799-0125-8",
pages = "328--332",
booktitle = "Multimedia Signal Processing (MMSP)",
publisher = "IEEE",
note = "Multimedia Signal Processing (MMSP), 2013 IEEE 15th International Workshop on ; Conference date: 30-09-2013 Through 02-10-2013",
}