Single-image specular reflection separation
View Patent ↗Systems and methods are discussed to separate the specular reflectivity and/or the diffuse reflectivity from an input image. Embodiments of the invention can be used to determine the specular chromaticity by iteratively solving one or more objective functions. An objective function can include functions that take into account the smooth gradient of the specular chromaticity. An objective function can take into account the interior chromatic homogeneity of the diffuse chromaticity and/or the sharp changes between chromaticity. Embodiments of the invention can also be used to determine the specular chromaticity of an image using a pseudo specular-free image that is calculated from the input image and a dark channel image that can be used to iteratively solve an objective function(s).
1. A method for providing a specular reflectivity from an input image comprising:
receiving the input image at a computer device, wherein the input image comprises a red channel, a green channel, and a blue channel for each pixel in the input image;
computing a cluster analysis on the input image that clusters each pixel in the input image into clusters having similar chromaticity, wherein the cluster analysis determines a chromaticity index for each pixel and a chromaticity vector that indicates an average chromaticity of each cluster represented by the chromaticity index;
determining, from an objective function, the specular reflectivity of the input image, wherein the objective function includes a function that specifies that the specular reflectivity is smooth across edges within the input image, and wherein the objective function additionally specifies that a diffuse reflectivity either i) is relatively constant within each cluster or ii) changes sharply between clusters; and
providing the specular reflectivity of the input image.
2. The method according to claim 1 , wherein the objective function additionally specifies that a diffuse reflectivity is relatively constant for the same chromaticity.
3. The method according to claim 1 , further comprising:
calculating a dark channel image of the input image, wherein the dark channel image comprises an image having for each pixel value a corresponding lowest pixel value of the corresponding red channel pixel, green channel pixel, and blue channel pixel of the input image; and
calculating a pseudo specular-free image as a difference between the input image and the dark channel image, wherein the computing the cluster analysis on the input image comprises computing the cluster analysis on the pseudo specular-free image.
4. A non-transitory computer-readable storage medium storing computer-executable program instructions for providing a specular reflectivity from an input image, the program instructions comprising:
program code for receiving the input image at a computer device, wherein the input image comprises a red channel, a green channel, and a blue channel for each pixel in the input image;
program code for computing a cluster analysis on the input image that clusters each pixel in the input image into clusters having similar chromaticity, wherein the cluster analysis determines a chromaticity index for each pixel and a chromaticity vector that indicates an average chromaticity of each cluster represented by the chromaticity index;
program code for determining, from an objective function, the specular reflectivity of the input image, wherein the objective function includes a function that specifies that the specular reflectivity is smooth across edges within the input image, and wherein the objective function additionally specifies that a diffuse reflectivity either i) is relatively constant within each cluster or ii) changes sharply between clusters; and
program code for providing the specular reflectivity of the input image.
5. The non-transitory computer-readable storage medium according to claim 4 , wherein the objective function additionally specifies that a diffuse reflectivity is relatively constant for the same chromaticity.
6. The non-transitory computer-readable storage medium according to claim 4 , the program instructions further comprising:
program code for calculating a dark channel image of the input image, wherein the dark channel image comprises an image having for each pixel value a corresponding lowest pixel value of the corresponding red channel pixel, green channel pixel, and blue channel pixel of the input image; and
program code for calculating a pseudo specular-free image as a difference between the input image and the dark channel image, wherein the computing the cluster analysis on the input image comprises computing the cluster analysis on the pseudo specular-free image.
7. A system for providing a specular reflectivity from an input image, the system comprising:
a digital storage device; and
a processor communicatively coupled to the digital storage device and configured to:
receive the input image, wherein the input image comprises a red channel, a green channel, and a blue channel for each pixel in the input image;
compute a cluster analysis on the input image that clusters each pixel in the input image into clusters having similar chromaticity, wherein the cluster analysis determines a chromaticity index for each pixel and a chromaticity vector that indicates an average chromaticity of each cluster represented by the chromaticity index;
store the chromaticity index and the chromaticity vector in the digital storage device;
solve an objective function to determine the specular reflectivity of the input image, wherein the objective function specifies that the specular reflectivity is smooth across edges within the input image, and wherein the objective function additionally specifies that a diffuse reflectivity either i) is relatively constant within each cluster or ii) changes sharply between clusters; and
provide the specular reflectivity of the input image.
8. The system according to claim 7 , wherein the objective function additionally specifies that a diffuse reflectivity is relatively constant for the same chromaticity.
9. The system according to claim 7 , wherein the processor is further configured to:
calculate a dark channel image of the input image, wherein the dark channel image comprises an image having for each pixel value a corresponding lowest pixel value of the corresponding red channel pixel, green channel pixel, and blue channel pixel of the input image; and
calculate a pseudo specular-free image as a difference between the input image and the dark channel image, wherein the computing the cluster analysis on the input image comprises computing the cluster analysis on the pseudo specular-free image.