Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that generate customized color editing options tailored to a digital image. In particular, in one or more embodiments, the disclosed systems generate an interactive editing user interface that includes selectable color controls corresponding to dominant colors extracted from the digital image and ordered by dominance. In at least one embodiment, the disclosed systems utilizes clustering techniques associated with the dominant representative colors to generate contour paths in the digital image further enabling dynamic interactive image editing.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that generate customized color editing options tailored to a digital image. In particular, in one or more embodiments, the disclosed systems generate an interactive editing user interface that includes selectable color controls corresponding to dominant colors extracted from the digital image and ordered by dominance. In at least one embodiment, the disclosed systems utilizes clustering techniques associated with the dominant representative colors to generate contour paths in the digital image further enabling dynamic interactive image editing.

Abstract: Certain embodiments involve generating recolored collages. For example, a method includes receiving a first image from and a second image. The method also includes grouping color hues within the first image into a first color hue cluster, and grouping color hues within the second image into a second color hue cluster. Further, the method includes determining that a first hue center of the first color hue cluster is within a distance range of a second hue center of the second color hue cluster. Additionally, the method includes generating a first recolored image by recoloring pixels of the first image having color hues outside the first color hue cluster and generating a second recolored image by recoloring pixels of the second image having color hues outside the second color hue cluster. Moreover, the method includes outputting a recolored collage including the first recolored image and the second recolored image.

Abstract: Saliency-based collage generation techniques are described. A collage generation module is executed by a computing device and receives multiple digital images. The collage generation module then generates multiple saliency maps from the digital images that describe a visual saliency of respective pixels in the digital images. The saliency maps are then used by the collage generation module to fit bounding boxes to portions of the digital images that are considered salient. Collage candidates are generated by the collage generation module based on predefined layouts and the bounding boxes that are fit the portions of the digital images. The collage generation module then selects at least one collage from these collage candidates for output to a user based on the determined amounts of deviation.

Abstract: Certain embodiments involve generating recolored collages. For example, a method includes receiving a first image from and a second image. The method also includes grouping color hues within the first image into a first color hue cluster, and grouping color hues within the second image into a second color hue cluster. Further, the method includes determining that a first hue center of the first color hue cluster is within a distance range of a second hue center of the second color hue cluster. Additionally, the method includes generating a first recolored image by recoloring pixels of the first image having color hues outside the first color hue cluster and generating a second recolored image by recoloring pixels of the second image having color hues outside the second color hue cluster. Moreover, the method includes outputting a recolored collage including the first recolored image and the second recolored image.

Abstract: Saliency-based collage generation techniques are described. A collage generation module is executed by a computing device and receives multiple digital images. The collage generation module then generates multiple saliency maps from the digital images that describe a visual saliency of respective pixels in the digital images. The saliency maps are then used by the collage generation module to fit bounding boxes to portions of the digital images that are considered salient. Collage candidates are generated by the collage generation module based on predefined layouts and the bounding boxes that are fit the portions of the digital images. The collage generation module then selects at least one collage from these collage candidates for output to a user based on the determined amounts of deviation.