The processing element 205 can be any type of electronic device or processor (e.g., processor 110) capable of processing, receiving, or transmitting instructions. For example, the processing element 205 can be a microprocessor or microcontroller. In some embodiments, components of the system can be controlled by a first processor and other components can be controlled by a second processor, where the first and second processors may or may not be in communication with each other. The device 200 may use one or more processing elements 205 or may utilize processing elements included in other components. For example, the device 200 can comprise a user device implementing at least a portion of the system 105, and other portions of the system may reside on a server.

The display 210 provides visual output to a user and optionally may receive user input (e.g., through a touch screen interface). The display 210 can be substantially any type of electronic display, including a liquid crystal display, organic liquid crystal display, and so on. The type and arrangement of the display depends on the desired visual information to be transmitted (e.g., can be incorporated into a wearable item such as glasses, or may be a television or large display, or a screen on a mobile device). The display 210 can be used to display pixel-based image data (e.g., 140 or 150 of FIG. 1) and pigment-based image data (e.g., 145 of FIG. 1).

The memory 215 (e.g., memory/storage 115) stores data used by the device 200 to store instructions for the processing element 205 and various data used by the system (e.g., pigment-based image data and pixel-based image data). The memory 215 can be, for example, magneto-optical storage, read only memory, random access memory, erasable programmable memory, flash memory, or a combination of one or more types of memory components. The memory 215 can include, for example, one or more non-transitory computer-readable media carrying instructions configured to cause the processing element 205 and/or the device 200 or other components of the system to perform operations described herein.

The I/O interface 220 provides communication to and from the various devices within the device 200 and components of the computing resources to one another. The I/O interface 220 can include one or more input buttons, a communication interface, such as WiFi, Ethernet, or the like, as well as other communication components, such as universal serial bus (USB) cables, or the like. In some implementations, the I/O interface 220 can be configured to receive voice inputs and/or gesture inputs.

The power source 225 provides power to the various computing resources and/or devices. The color space mapping system may include one or more power sources, and the types of power source may vary depending on the component receiving power. The power source 225 may include one or more batteries, a wall outlet, a cable cord (e.g., USB cord), or the like.

The sensors 230 may include components for providing inputs of the system, such as a camera for providing pixel-based image data. Additionally or alternatively, sensors 230 can be used to provide other inputs, such as gesture-based controls.

Components of the device 200 are illustrated only as examples, and illustrated components can be removed from or added to the device 200 without deviating from the teachings of the present disclosure. In some implementations, components of the device 200 can be included in multiple devices, such as a user device and a server.

FIG. 3 is a flow diagram illustrating a process 300 performed using a color space mapping system. The process can be performed using the system 105 of FIG. 1 or the computing device 200 of FIG. 2. The process 300 can be used to convert a pixel-based image to a pigment-based color space for applying modifications to the image before converting the modified image back to a pixel-based color space. For example, the process 300 allows a digital photograph to be modified in the pigment-based color space using effects to simulate painting techniques, and the process 300 enables conversion of the modified image back to the pixel-based color space for further processing (e.g., for creating photo prints or standard digital images).

The process begins at block 310, where first image data is received comprising first color information in a first color space. The first image data can comprise pixel-based image data including pixel color information using a pixel-based color space, such as a RGB color space. For example, the first image data can be a digital photograph captured using a digital camera. The first color space can use an additive model, where colors are representing based on values of different color components (e.g., red, green, and blue).

At block 320, second image data is generated using the first image data, the second image data comprising second color information in a second color space. For example, pigment-based image data can be generated comprising pigment color information using a pigment-based color space, such as a color space using a Kubelka-Munk color model. Unlike the first color space, the second color space can simulate behaviors or characteristics of pigments, such as color blending that simulates paint characteristics. The conversion from the first color space to the second color space can use a machine learning model to determine color values in the pigment-based color space for color values in the pixel-based color space. Machine learning is used to determine the color values in the second color space because there is not a one-to-one correlation between values in the second color space and the first color space, so existing systems may lack a simple algorithmic approach for determining color values in the second color space based on color values in the first color space. As a result, existing techniques cannot be used to convert from the first color space to the second color space while retaining visual characteristics of the image (e.g., beyond a threshold accuracy).

In an embodiment, the second color space comprises an extended color space that uses color values comprising pigment-based color values and residual values representing adjustments or values of corresponding pixel-based colors.

In various embodiments, supplemental color data is generated as part of generating the second image data. The supplemental color data is generated to provide additional information for converting image data from the second color space to the first color space. In other words, because color values in the first color space may correspond to multiple potential color values in the second color space, the supplemental color data is needed to determine an appropriate (e.g., closest) color value in the first color space for a respective color value in the second color space. Some embodiments provide multiple data channels (e.g., three or more channels) of supplemental color data in an extended color map, which can be residual pixel-based color data specifying adjustments or values in a pixel-based color space. Embodiments of the color space mapping system train and provide a machine learning model to generate the supplemental color data (e.g., using the process 400 of FIG. 4) and/or color values in an extended color map.