Encoding and decoding based on blending of sequences of samples along time

1. A method comprising:

receiving image settings for each of multiple images in a sequence;

combining the image settings of the multiple images in the sequence to produce image settings of a baseline image, the baseline image being representative of the sequence of multiple images; and

for each respective image in the sequence of multiple images, producing hierarchical reconstruction data indicating corresponding image processing operations and adjustment data specifying how to reconstruct a corresponding rendition of the respective image from the baseline image.

2. The method as in claim 1 , wherein combining the image settings includes:

overlaying the multiple images with respect to each other; and

using the overlaid images to produce the baseline image representative of the sequence.

3. The method as in claim 1 , wherein each of the multiple images in the sequence is received in accordance with a first resolution, the method further comprising:

producing the baseline image to be at a second resolution, the second resolution lower than the first resolution.

4. The method as in claim 3 , wherein each of the multiple images in the sequence includes a rendition of a particular object; and

wherein combining the image settings includes: producing a rendition of the particular object in the baseline image based on a combination of renditions of the particular object in each of the multiple images.

5. The method as in claim 1 , wherein a first image of the multiple images in the sequence includes settings corresponding to a respective unique visual artifact not found in images other than the first image; and

wherein combining includes producing the baseline image to include settings corresponding to the unique visual artifact.

6. The method as in claim 1 , wherein the sequence of multiple images includes at least a first image and a second image;

wherein receiving the image settings includes:

retrieving a setting of an element in the first image, the element in the first image representing a particular portion of an object in the first image;

retrieving a setting of an element in the second image, the element in the second image representing the particular portion of the object in the second image.

7. The method as in claim 6 , wherein combining the image settings includes:

computing a setting for the particular portion of the object in the baseline image based at least in part on a combination of the setting for the element in the first image and the setting for the element in the second image.

8. The method as in claim 1 , wherein the baseline image is of a lower resolution than a resolution of the multiple images in the sequence.

9. The method as in claim 8 , wherein each of the multiple images in the sequence includes settings corresponding to a rendition of a particular object; and

wherein combining the multiple images includes: producing a rendition of the particular object in the baseline image based on a combination of settings corresponding with different renditions of the object in the sequence of multiple images.

10. The method as in claim 8 , wherein combining image settings includes:

stacking the multiple images with respect to each other;

processing one or more of the multiple images in the stack to align settings of corresponding objects in the multiple images; and

via combining settings of corresponding elements of the multiple images in the stack, producing the baseline image.

11. The method as in claim 8 , wherein the sequence of multiple images includes at least a first image and a second image;

wherein receiving the image settings includes:

retrieving a setting of an element in the first image, the setting of the element in the first image corresponding to a particular portion of an object rendered in the first image; and

retrieving a setting of an element in the second image, the element in the second image corresponding to the particular portion of the object in the second image.

12. The method as in claim 11 , wherein combining the image settings includes:

computing a setting for a particular region of the object in the baseline image based at least in part on a combination of the setting of the element in the first image and the setting of the element in the second image.

13. The method as in claim 1 further comprising:

producing meta information indicating how many of the multiple images in the sequence were used to derive the baseline image.

14. The method as in claim 1 , wherein the baseline image includes multiple renditions of a same object present in a set of two of the multiple images in the sequence.

15. The method as in claim 14 , wherein the set of two images in the sequence includes a first image and a second image; and

wherein a rendition of the common object in the first image is disposed at a spatially different location than a rendition of the object in the second image.

16. The method as in claim 1 , wherein combining the image settings includes:

temporally combining the multiple images in the sequence; and

downsampling the temporally combined images to produce the settings of the baseline image.

17. The method as in claim 16 further comprising:

producing the hierarchical reconstruction data based on the downsampling.

18. The method as in claim 1 , wherein the image processing operation includes an upsampling operation.

19. The method as in claim 16 , wherein the image settings for the multiple images in the sequence define the multiple images at a first resolution; and

wherein the image settings of the baseline image are defined at a second resolution, the second resolution lower than the first resolution.

20. The method as in claim 18 further comprising:

producing the hierarchical reconstruction data to specify at least one upsample operation to apply to the baseline image to reproduce a first image in the sequence.

21. The method as in claim 1 further comprising:

applying at least one downsampling operation to produce the settings of the baseline image.

22. Computer-readable storage hardware having instructions stored thereon, the instructions, when carried out by computer processor hardware, cause the computer processor hardware to:

receive image settings for each of multiple images in a sequence;

combine the image settings of the multiple images in the sequence to produce image settings of a baseline, the baseline image being representative of the sequence of multiple images; and

for each respective image in the sequence, produce hierarchical reconstruction data indicating corresponding image processing operations and adjustment data specifying how to reconstruct a corresponding rendition of the respective image from the baseline image.