US 2025/0061582 A1 · Image Processing To Detect Edges, Walls, And Surfaces For A Virtual Painting Application

Abstract

A method includes uploading an image and a final edge map to a computing device, the image being a scene having at least one wall, at least one shadow, and at least one highlight, processing the image using a Segment-Anything model forming a processed image, performing wall segmentation on the processed image using the segment-anything model, performing segmentations of the processed image to generate a coarse wall mask, establishing a dynamic threshold of high confidence pixels to exclude small wall contours coordinates, performing a semi-random seed point generation, running the processed image through a second pass of the segment-anything model to remove additional segments below predetermined acceptable thresholds for noise before establishing a final predicted wall, generating the final predicted wall including a colorized image by applying color to the segmented wall to paint the at least one wall, and displaying the colorized image on a display.

Claims25

Dependent claims

A method comprising:

uploading an image and a final edge map to a computing device, the image being a scene having at least one wall, at least one shadow, and at least one highlight;
processing the image using a Segment-Anything model forming a processed image;
performing wall segmentation on the processed image using the segment-anything model;
performing segmentations of the processed image to generate a coarse wall mask;
establishing a dynamic threshold of high confidence pixels to exclude small wall contours coordinates;
performing a semi-random seed point generation along a horizontal axis of the processed image;
running the processed image through a second pass of the segment-anything model to remove additional segments below predetermined acceptable thresholds for noise before establishing a final predicted wall;
generating the final predicted wall including a colorized image by applying color to the segmented wall to paint the at least one wall;
and
displaying the colorized image on a display of the computing device.

7 more elements

A system comprising a computing device having a processor and a memory, the computing device being configured to:

receive an image and a final edge map uploaded to the computing device, where the image is of a scene having at least one wall and the scene includes at least one shadow and at least one highlight;
perform image segmentation;
perform an image mask, where the image mask includes a segment wall coordinates of the wall;
perform a grayscale function on the image to generate a grayscale image;
perform a transparency function on the image to generate an alpha gray image, where the alpha gray image represents the at least one shadow as an opaque region and represents the at least one highlight as a transparent region;
perform a normalization function on the image to generate a re-gray image, where the normalization function includes measuring one or more values of at least one pixel of the image and normalizing the one or more values;
generate a colorized image by applying a color to the final edge map and using the grayscale image, alpha gray image and re-gray image;
and
display the colorized image on a display of the computing device.

6 more elements

Dependencies are inferred from the claim text.

Image Processing To Detect Edges, Walls, And Surfaces For A Virtual Painting Application

Life of this patent

Image Processing To Detect Edges, Walls, And Surfaces For A Virtual Painting Application

Life of this patent

Abstract

Claims25