Abstract: A method for restoration of a captured image includes: blurring the captured image based on removing high spatial frequency content and maintaining colour characteristics of the captured image; generating a global colour attention map corresponding to the blurred captured image, where the global colour attention map indicates spatial representation of colour composition among regions within the blurred captured image; splitting the captured image into a plurality of patches; extracting one or more task features from the plurality of patches, where the one or more task features indicate characteristics related to a corresponding task; and generating stitched features corresponding to the plurality of patches, respectively, based on correlating the one or more task features and the global colour attention map, where the stitched features indicate an integrated representation of the captured image based on a global context and the corresponding task.

Abstract: A method for correcting a blur in media, may include: receiving an input image indicating a degraded document comprising text regions and non-text regions; generating a blur localization map from the input image to detect a presence of a plurality of blur regions in the text regions and the non-text regions; estimating a degree of blur in the text regions of the plurality of blur regions by generating a text blur estimation map, to deblur the text regions based on a corresponding level of degradations; and generating a blur attention map by fusing the blur localization map and the text blur estimation map to output a location and a strength of the blur in the text regions.

Abstract: A method of detecting blur in an input image, the method including: detecting one or more candidate blur regions of a plurality of regions in the input image; determining, a first confidence score of the one or more candidate blur regions in the input image; determining a second confidence score of a global blur in the input image; determining a third confidence score of an intentional blur in the input image; and detecting a type of blur and a strength of the type of blur in the input image based on the first confidence score of the one or more candidate blur regions, the second confidence score of the global blur, and the third confidence score of the intentional blur.

Abstract: A method for performing multi-functional image restoration by an electronic device with a trained Machine Learning (ML) model is provided. The method includes receiving an image and determining channels of the image, and determining whether a number of restructuring needed for the channels is one. When the restructuring needed for the channels not one, then the method includes restructuring each channel into a first channel set, generating first inferences of the image corresponding to each channel by feeding the first channel set to the trained ML model, and generating a final inference image by combining the first inferences. When the number of restructuring needed for the channels is one, then the method includes restructuring the channels into a second channel set, and generating a second inference of the image by feeding the second channel set to the trained ML model.