Generating images using neural networks

1. A computer-implemented method of generating an output image comprising a plurality of pixels arranged in a two-dimensional map, each pixel having a respective value for each of one or more channels, wherein the method comprises:

receiving an input image by a neural network system;

processing the input image using one or more initial neural network layers of the neural network system to generate a respective portion of an alternative representation of the input image corresponding to each of the one or more channels for each pixel in the plurality of pixels included in the output image; and

for each of the one or more channels for each pixel in the plurality of pixels included in the output image:

processing the respective portion of the alternative representation using one or more output neural network layers to generate a respective score distribution over a discrete set of possible values for the channel, wherein the respective score distribution comprises a score for each of the possible values in the discrete set; and

selecting, using the respective score distribution and from the discrete set of possible values for the channel, the respective value for the channel.

2. The method of claim 1 , wherein the output image is a different image than the input image.

3. The method of claim 2 , wherein the output image is temporally related to the input image.

4. The method of claim 3 , wherein the output image depicts a same object as the input image with a different pose.

5. The method of claim 2 , wherein the input image is a previously generated output image of the neural network system.

6. The method of claim 1 , wherein the output image is a reconstruction of the input image.

7. The method of claim 1 , wherein the one or more initial neural network layers comprise convolutional neural network layers.

8. The method of claim 7 , wherein the convolutional neural network layers are spatial resolution-preserving convolutional neural network layers.

9. The method of claim 1 , wherein the one or more initial neural network layers are configured to generate the alternative representations in a sequential order.

10. The method of claim 1 , wherein the one or more initial neural network layers are configured to generate the alternative representations in parallel by using respective values for each of one or more channels for a plurality of pixels in the input image.

11. A system comprising one or more computers and one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations for generating an output image comprising a plurality of pixels arranged in a two-dimensional map, each pixel having a respective value for each of one or more channels, wherein the operations comprise:

receiving an input image by a neural network system;

processing the input image using one or more initial neural network layers of the neural network system to generate a respective portion of an alternative representation of the input image corresponding to each of the one or more channels for each pixel in the plurality of pixels included in the output image; and

for each of the one or more channels for each pixel in the plurality of pixels included in the output image:

processing the respective portion of the alternative representation using one or more output neural network layers to generate a respective score distribution over a discrete set of possible values for the channel, wherein the respective score distribution comprises a score for each of the possible values in the discrete set; and

selecting, using the respective score distribution and from the discrete set of possible values for the channel, the respective value for the channel.

12. The system of claim 11 , wherein the output image is a different image than the input image.

13. The system of claim 12 , wherein the output image is temporally related to the input image.

14. The system of claim 13 , wherein the output image depicts a same object as the input image with a different pose.

15. The system of claim 12 , wherein the input image is a previously generated output image of the neural network system.

16. The system of claim 11 , wherein the output image is a reconstruction of the input image.

17. The system of claim 11 , wherein the one or more initial neural network layers comprise convolutional neural network layers.

18. The system of claim 17 , wherein the convolutional neural network layers are spatial resolution-preserving convolutional neural network layers.

19. The system of claim 11 , wherein the one or more initial neural network layers are configured to generate the alternative representations in a sequential order.

20. One or more non-transitory computer-readable storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations for generating an output image comprising a plurality of pixels arranged in a two-dimensional map, each pixel having a respective value for each of one or more channels, wherein the operations comprise:

receiving an input image by a neural network system;

processing the input image using one or more initial neural network layers of the neural network system to generate a respective portion of an alternative representation of the input image corresponding to each of the one or more channels for each pixel in the plurality of pixels included in the output image; and

for each of the one or more channels for each pixel in the plurality of pixels included in the output image:

processing the respective portion of the alternative representation using one or more output neural network layers to generate a respective score distribution over a discrete set of possible values for the channel, wherein the respective score distribution comprises a score for each of the possible values in the discrete set; and

selecting, using the respective score distribution and from the discrete set of possible values for the channel, the respective value for the channel.