Adding greater realism to a computer-generated image by smoothing jagged edges
During the rendering of an image, specific pixels in the image are identified where antialiasing would be helpful. Antialiasing is then performed on these identified pixels, where anti-aliasing is a technique used to add greater realism to a digital image by smoothing jagged edges. This reduces a cost of performing antialiasing by reducing a number of pixels within an image on which antialiasing is performed.
1. A processor comprising:
one or more circuits to cause one or more anti-aliasing algorithms to be selected from among a plurality of different anti-aliasing algorithms to correct one or more miscolored pixels in one or more digital images based, at least in part, on whether the miscolored pixels correspond to one or more edges of one or more features depicted in the one or more digital images.
2. The processor of claim 1 , wherein the one or more miscolored pixels are identified utilizing source geometry.
3. The processor of claim 1 , wherein the one or more digital images are created utilizing one of forward rendering, deferred rendering, or ray tracing.
4. The processor of claim 1 , wherein the one or more miscolored pixels are identified during temporal antialiasing (“TAA”),
wherein the TAA compares an historical value for a pixel in a previous frame to current values of neighboring pixels in a current frame, and
wherein the pixel with the historical value differs from the current values of neighboring pixels by more than a predetermined amount.
5. The processor of claim 1 , wherein a pixel of the one or more miscolored pixels has a depth value that differs from depth values for neighboring pixels by more than a predetermined amount.
6. The processor of claim 1 , wherein a pixel of the at one or more miscolored pixels has a luminance value that differs from luminance values for neighboring pixels by more than a predetermined amount.
7. The processor of claim 1 , wherein the one or more miscolored pixels are marked using a sentinel value.
8. The processor of claim 1 , wherein the one or more miscolored pixels are included within a segmentation mask.
9. The processor of claim 4 , wherein performing the TAA includes determining point-sampling visibility for a sub-pixel area within at least one of the one or more miscolored pixels.
10. A system comprising:
one or more processors to cause one or more anti-aliasing algorithms to be selected from among a plurality of different anti-aliasing algorithms to correct one or more miscolored pixels in one or more digital images based, at least in part, on whether the miscolored pixels correspond to one or more edges of one or more features depicted in the one or more digital images; and
memory that is configured to store results of the one or more anti-aliasing algorithms.
11. The system of claim 10 , wherein the one or more miscolored pixels are identified utilizing source geometry.
12. The system of claim 10 , wherein the one or more digital images are created utilizing one of forward rendering, deferred rendering, or ray tracing.
13. The system of claim 10 , wherein a pixel of the one or more miscolored pixels has a depth value that differs from depth values for neighboring pixels by more than a predetermined amount.
14. The system of claim 10 , wherein a pixel of the at one or more miscolored pixels has a luminance value that differs from luminance values for neighboring pixels by more than a predetermined amount.
15. The system of claim 10 , the one or more miscolored pixels are marked using a sentinel value.
16. The system of claim 10 , wherein the one or more miscolored pixels are included within a segmentation mask.
17. A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to:
cause one or more anti-aliasing algorithms to be selected from among a plurality of different anti-aliasing algorithms to correct one or more miscolored pixels in one or more digital images based, at least in part, on whether the miscolored pixels correspond to one or more edges of one or more features depicted in the one or more digital images.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the miscolored pixels are identified utilizing source geometry.
19. The non-transitory computer-readable storage medium of claim 17 , wherein a pixel of the one or more miscolored pixels has a depth value that differs from depth values for neighboring pixels by more than a predetermined amount.
20. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions, when executed by the processor, further cause the processor to:
create an output image by blending textures, with a color buffer, results of the ray tracing.