Spatio-temporal noise masks and sampling using vectors for image processing and light transport simulation systems and applications

1. A computer-implemented method for generating a texture, the method comprising:

receiving a texture including two or more pixels;

computing a texture energy value for the texture based on an energy function,

wherein the energy function is based on a distance between a pair of pixels of the two or more pixels, and one or more configurable parameters,

wherein the texture energy value is based on a summation of pixel energy values for pixels in the texture, and

wherein a pixel energy value for each pixel in the pair of pixels comprises a non-zero value as a result of at least one of: the pair of pixels being in a same multi-dimensional layer, or the pair of pixels having identical coordinates at different temporal slices;

swapping positions of pixels from pairs of pixels in the texture until the texture energy value reaches a minimum energy value based on the energy function; and

generating an output texture including output pixels based on the texture with minimum energy value to be applied to image data.

2. The computer-implemented method of claim 1 , wherein the texture is a white noise texture.

3. The computer-implemented method of claim 1 , wherein the energy function is further based on one or more sample values associated with the pair of pixels.

4. The computer-implemented method of claim 1 , wherein at least one pixel of the two or more pixels corresponds to at least one of: one or more vectors, one or more points on a mesh, or one or more objects with more than three dimensions, and wherein the output texture is to be applied to image data that includes vectors, points on a mesh, or objects with more than three dimensions.

5. The computer-implemented method of claim 1 , wherein prior to computing the energy value for the texture, the method further comprising:

sampling one or more pixels corresponding to the image data, wherein each pixel corresponds to a random variable, wherein the sampling one or more pixels corresponds to determining a value for a probability density function for a pixel, and wherein the sampling includes reducing a variance of samples by skewing samples towards regions of higher energy based on the energy function.

6. The computer-implemented method of claim 1 , wherein the one or more configurable parameters comprise a first configurable parameter and a second configurable parameter, the first configurable parameter comprising a Gaussian value, and the second configurable parameter comprising a different Gaussian value from the first configurable parameter.

7. The computer-implemented method of claim 1 , the method further comprising:

prior to computing the energy value for the texture, sampling one or more pixels corresponding to the image data, wherein each pixel corresponds to a random variable, wherein the sampling one or more pixels comprises at least one of: determining a value for a probability density function for a pixel, or performing non-uniform sampling.

8. The computer-implemented method of claim 1 , further comprising:

applying a low discrepancy sequence to the output texture to add an additional dimension to each output pixel.

9. The computer-implemented method of claim 1 , further comprising:

inputting one or more scalar output pixel values into a space-filling curve function to output one or more pixel values that are vectors.

10. The computer-implemented method of claim 1 , further comprising:

stratifying the texture into strata over time;

calculating a stratification score based on a number of pixel values in each stratum in which a pixel of the pair of pixels is located; and

rejecting a swap of pixels if the swap increases the stratification score.

11. The computer-implemented method of claim 1 , further comprising:

applying a low pass filter to the image data.

12. The computer-implemented method of claim 1 , wherein swapping further comprises selecting two or more random pairs of pixels to swap.

13. A processor comprising:

one or more processing units to perform a plurality of operations including:

receiving a texture including two or more pixels;

computing a texture energy value for the texture based on an energy function,

wherein the energy function is based on a distance between a pair of pixels of the two or more pixels, and one or more configurable parameters,

wherein the texture energy value is based on a summation of pixel energy values for pixels in the texture, and

wherein a pixel energy value for each pixel in the pair of pixels comprises a non-zero value as a result of at least one of: the pair of pixels being in a same multi-dimensional layer, or the pair of pixels having identical coordinates at different temporal slices;

swapping positions of pixels from pairs of pixels in the texture until the texture energy value reaches a minimum energy value based on the energy function;

generating an output texture including output pixels based on the texture with minimum energy value to be applied to image data; and

rendering an output image over multiple frames based on applying the texture to the one or more images.

14. The processor of claim 13 , wherein sampling one or more pixels corresponding to the image data, wherein each pixel corresponds to a random variable, wherein the sampling one or more pixels corresponds to determining a value for a probability density function for a pixel, and wherein the sampling includes reducing a variance of samples by skewing the samples towards regions of higher energy based on the energy function.

15. The processor of claim 13 , wherein the texture is a white noise texture.

16. The processor of claim 13 , wherein at least one pixel of the two or more pixels corresponds to at least one of: one or more vectors, one or more points on a mesh, or one or more objects with more than three dimensions, and wherein the output texture is to be applied to image data that includes vectors, points on a mesh, or objects with more than three dimensions.

17. The processor of claim 13 , wherein the operations further comprise:

sampling one or more pixels corresponding to the image data, wherein each pixel corresponds to a random variable, wherein the sampling one or more pixels corresponds to determining a value for a probability density function for a pixel, and wherein the sampling includes reducing a variance of the samples by skewing cosine-weighted samples towards regions of higher energy based on the energy function.

18. The processor of claim 13 , wherein the operations further comprise:

applying a rank-1 lattice to add an additional dimension to the output texture.

19. The processor of claim 13 , wherein the operations further comprise:

inputting one or more scalar output pixel values into a space-filling curve function to output one or more pixel values that are vectors.

20. A non-transitory computer-readable storage medium having stored thereon one or more instructions, which if performed by one or more processors, cause one or more processors to perform operations comprising:

receiving a texture including two or more pixels;

computing a texture energy value for the texture based on an energy function,

wherein the energy function is based on a distance between a pair of pixels of the two or more pixels, and one or more configurable parameters,

wherein the texture energy value is based on a summation of pixel energy values for pixels in the texture, and

wherein a pixel energy value for each pixel in the pair of pixels comprises a non-zero value as a result of at least one of: the pair of pixels being in a same multi-dimensional layer, or the pair of pixels having identical coordinates at different temporal slices;

swapping positions of pixels within pairs of pixels in the texture until the texture reaches a minimum energy value based on the energy function; and

generating an output texture including output pixels based on the texture with minimum energy value to be applied to image data.

21. The non-transitory computer-readable storage medium of claim 20 , wherein a texture is stratified through time, and further comprising rejecting a pixel swap based on a number of pixel values found in strata of the texture.

22. The non-transitory computer-readable storage medium of claim 20 , wherein the texture includes a temporal dimension.

23. The non-transitory computer-readable storage medium of claim 20 , further comprising:

sampling one or more pixels corresponding to the image data, wherein each pixel corresponds to a random variable, wherein the sampling one or more pixels corresponds to determining a value for a probability density function for a pixel, and wherein the sampling includes reducing a variance of samples by skewing the samples towards regions of greater light reflection based on the energy function.

24. The non-transitory computer-readable storage medium of claim 20 , wherein the operations further comprise:

setting the energy value of a pixel to a zero value if the pixel and another pixel are not in a same multi-dimensional layer or do not have identical coordinates.

25. The non-transitory computer-readable storage medium of claim 20 , wherein the one or more configurable parameters comprise a first configurable parameter and a second configurable parameter, the first configurable parameter comprising an energy falloff parameter corresponding to how energy dissipates from a pixel, and the second configurable parameter corresponding to a normal distribution of energy.

26. The non-transitory computer-readable storage medium of claim 20 , further comprising:

inputting one or more scalar output pixel values into a space-filling curve function to output one or more pixel values that are vectors.

27. The non-transitory computer-readable storage medium of claim 20 , wherein the operations further comprise:

applying a low pass filter to the image data.

28. The non-transitory computer-readable storage medium of claim 20 , wherein a number of swaps corresponds to a width, height, and depth of the texture.

29. The non-transitory computer-readable storage medium of claim 20 , wherein the energy function has a non-zero value as a result of the pair of pixels having identical z coordinates.