Machine learning techniques for generating product imagery and their applications
Techniques for generating images of furniture and using the generated images for image-based search. The techniques include obtaining a first image depicting first furniture, generating, using the first image and a neural network model, a second image depicting second furniture different from the first furniture, searching for one or more images of furniture similar to the second furniture using the second image to obtain search results comprising a third image of furniture, and outputting the third image.
1. A method, comprising:
using at least one computer hardware processor to perform:
obtaining an input image depicting first furniture, wherein obtaining the input image comprises:
generating multiple images using respective points in a latent space associated with a neural network model;
presenting the multiple images to a user using a graphical user interface; and
receiving, using the graphical user interface, input indicative of a selection of one of the multiple images;
obtaining, using the graphical user interface, at least one user selection indicative of a change in at least one furniture characteristic; and
generating, using the neural network model, the input image, and the at least one user selection, an output image depicting second furniture different from the first furniture.
2. The method of claim 1 , wherein obtaining the input image comprises:
receiving the input image over at least one communication network or accessing the input image from a non-transitory computer-readable storage medium.
3. The method of claim 1 , wherein generating the multiple images comprises selecting the respective points in the latent space at random.
4. The method of claim 1 , wherein generating the output image comprises:
mapping the input image to a first point in the latent space associated with the neural network model;
identifying a second point in the latent space using the first point and the at least one user selection; and
generating the output image using the second point in the latent space.
5. The method of claim 4 , wherein the latent space is one of an input latent space associated with the neural network model or an intermediate latent space associated with the neural network model.
6. The method of claim 5 , wherein the latent space is the intermediate latent space, wherein the first point comprises a plurality of values, wherein identifying the second point comprises identifying one or more changes in the plurality of values based on the at least one user selection.
7. The method of claim 5 , wherein the neural network model comprises a generative network, the generative network comprising:
a mapping network configured to map a point in the input latent space to a point in the intermediate latent space; and
a synthesis network configured to generate images from respective points in the intermediate latent space.
8. The method of claim 7 , wherein generating the output image is performed using the synthesis network, and generating the output image further comprises:
performing operations in a plurality of layers in the synthesis network based on a plurality of control values each associated with a respective one of the plurality of layers.
9. The method of claim 8 , wherein a point in the intermediate latent space has a plurality of values associated with respective dimensions in the intermediate latent space, and the method further comprising providing the plurality of control values based on one or more values of the point in the intermediate latent space.
10. The method of claim 5 , wherein the first point and the second point are in the input latent space or the intermediate latent space.
11. The method of claim 4 , wherein mapping the input image to the first point is performed using an iterative optimization technique to minimize an error between an image generated by the neural network model from a point in the latent space and the input image.
12. The method of claim 11 , wherein mapping the input image to the first point is performed further using an encoder network to determine an initial point in the latent space.
13. The method of claim 1 , further comprising:
displaying, in the graphical user interface, a graphical user element through which the user can provide the at least one user selection indicative of the change in the at least one furniture characteristic.
14. The method of claim 13 , wherein the graphical user element is a slide bar having a value range corresponding to the at least one furniture characteristic.
15. The method of claim 1 , further comprising:
transmitting the output image over at least one communication network to another electronic device.
16. The method of claim 1 , further comprising using the output image to search for one or more images of furniture similar to the second furniture in the output image.
17. The method of claim 1 , further comprising displaying the output image on a webpage, in a virtual reality (VR) environment or an augmented reality (AR) environment.
18. A system, comprising:
at least one computer hardware processor; and
at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform:
obtaining an input image depicting first furniture, wherein obtaining the input image comprises:
generating multiple images using respective points in a latent space associated with a neural network model;
presenting the multiple images to a user using a graphical user interface; and
receiving, using the graphical user interface, input indicative of a selection of one of the multiple images;
obtaining, using the graphical user interface, at least one user selection indicative of a change in at least one furniture characteristic; and
generating, using the neural network model, the input image, and the at least one user selection, an output image depicting second furniture different from the first furniture.
19. At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform:
obtaining an input image depicting first furniture, wherein obtaining the input image comprises:
generating multiple images using respective points in a latent space associated with a neural network model;
presenting the multiple images to a user using a graphical user interface; and
receiving, using the graphical user interface, input indicative of a selection of one of the multiple images;
obtaining, using the graphical user interface, at least one user selection indicative of a change in at least one furniture characteristic; and
generating, using the neural network model, the input image, and the at least one user selection, an output image depicting second furniture different from the first furniture.