Background separation for guided generative models
Embodiments of the present disclosure include obtaining an input image and an approximate mask that approximately indicates a foreground region of the input image. Some embodiments generate an unconditional mask of the foreground region based on the input image. A conditional mask of the foreground region is generated based on the input image and the approximate mask. Then, an output image is generated based on the unconditional mask and the conditional mask. In some cases, the output image includes the foreground region of the input image.
1. A method comprising:
obtaining an input image and an approximate mask that approximately indicates a foreground region of the input image;
generating, by an unconditional mask network, an unconditional mask of the foreground region based on the input image;
generating, by a conditional mask network, a conditional mask of the foreground region based on the input image and the approximate mask; and
generating an output image including the foreground region of the input image based on the unconditional mask and the conditional mask.
2. The method of claim 1 , wherein generating the output image comprises:
combining the unconditional mask and the conditional mask to obtain a combined mask, wherein the output image is generated based on the combined mask.
3. The method of claim 1 , wherein:
the input image is generated based on the approximate mask.
4. The method of claim 1 , wherein generating the output image comprises:
computing a distance transformation map based on the approximate mask, wherein the output image is generated based on the distance transformation map.
5. The method of claim 1 , wherein generating the output image comprises:
computing a color distance map based on the approximate mask, wherein the output image is generated based on the color distance map.
6. The method of claim 1 , wherein generating the output image comprises:
performing island removal on the input image, wherein the output image is generated based on the island removal.
7. The method of claim 1 , wherein:
the foreground region comprises text based on a font and modified with a text effect, and wherein the approximate mask is based on the text and the font without the text effect.
8. The method of claim 1 , wherein:
the unconditional mask comprises a probability mask and the conditional mask comprises a refined probability mask.
9. The method of claim 1 , wherein:
the unconditional mask network is trained to generate the unconditional mask of the foreground region based on the input image and the conditional mask network is trained to generate the conditional mask of the foreground region based on the input image and the approximate mask.
10. A method comprising:
initializing an unconditional mask network and a conditional mask network;
receiving training data including an input image, an approximate mask indicating a foreground region of the input image, and a ground-truth mask;
training, using the training data, the unconditional mask network to generate an unconditional mask of the foreground region based on the input image; and
training, using the training data, the conditional mask network to generate a conditional mask of the foreground region based on the input image and the approximate mask.
11. The method of claim 10 , further comprising:
combining the unconditional mask and the conditional mask to obtain a combined mask, wherein an output image is generated based on the combined mask.
12. The method of claim 10 , wherein:
the foreground region comprises text based on a font and modified with a text effect, and wherein the approximate mask is based on the text and the font without the text effect.
13. The method of claim 10 , wherein:
the conditional mask comprises a refined probability mask.
14. An apparatus comprising:
at least one processor;
at least one memory including instructions executable by the at least one processor;
a user interface comprising parameters stored in the at least one memory and configured to obtain an input image and an approximate mask that approximately indicates a foreground region of the input image;
an unconditional mask network comprising parameters stored in the at least one memory and configured to generate an unconditional mask of the foreground region based on the input image; and
a conditional mask network comprising parameters stored in the at least one memory and configured to generate a conditional mask of the foreground region based on the input image and the approximate mask.
15. The apparatus of claim 14 , further comprising:
an image generation model configured to generate an output image including the foreground region of the input image based on the unconditional mask and the conditional mask.
16. The apparatus of claim 15 , further comprising:
a distance transform component configured to compute a distance transformation map based on the approximate mask, wherein the output image is generated based on the distance transformation map.
17. The apparatus of claim 15 , further comprising:
a color distance component configured to compute a color distance map based on the approximate mask, wherein the output image is generated based on the color distance map.
18. The apparatus of claim 15 , further comprising:
an island removal component configured to perform island removal on the input image, wherein the output image is generated based on the island removal.
19. The apparatus of claim 15 , further comprising:
a mask combination component configured to combine the unconditional mask and the conditional mask to obtain a combined mask, wherein the output image is generated based on the combined mask.
20. The apparatus of claim 14 , further comprising:
a text-effect model configured to generate the input image.