Systems and methods for correcting color of uncalibrated material is disclosed. Example embodiments include a system to correct color of uncalibrated material. The system may include a non-transitory computer-readable medium operatively coupled to processors. The non-transitory computer-readable medium may store instructions that, when executed cause the processors to perform a number of operations. One operation is to obtain a target image of a degraded target material with one or more objects. The degraded target material comprises degraded colors and light information corresponding to light sources in the degraded target material. Another operations is to obtain color reference data. Another operation is to identify an object in the target image that corresponds to the color reference data. Yet another operation is to correct the identified object in the target image. Another operation is to correct the target image.

A system for manipulating images according to styles chosen by a user includes a feed-forward image manipulation model for everyday use and an optimization image manipulation model for more professional use. The optimization image manipulation model optimizes directly over output image pixels to minimize both the content loss and style loss. Users can select their own content and style images, and can choose between using the feed-forward image manipulation model and optimization image manipulation model.

From a first image using a model, a first uncertainty map is generated. An uncertainty level of a location in the first uncertainty map corresponds to a detection of a known structure in a portion of the first image. A first weighted image corresponding to the first uncertainty map is generated, the generating including assigning a first weight to a pixel of the first image, the first weight corresponding to the uncertainty level of a location in the first uncertainty map corresponding to the pixel. From a second image using a model, a second uncertainty map is generated. A second weighted image corresponding to the second uncertainty map is generated. The first image and the second image are combined to form a composite image, each image participating in the composite image according to the corresponding weighted image.

Various disclosed embodiments are directed to inpainting one or more portions of a target image based on merging (or selecting) one or more portions of a warped image with (or from) one or more portions of an inpainting candidate (e.g., via a learning model). This, among other functionality described herein, resolves the inaccuracies of existing image inpainting technologies.

Techniques for enhancing an image are described. For example, a lower-resolution image from a video file may be enhanced using a trained neural network applying the trained neural network on the lower-resolution image to remove artifacts by removing artifacts by generating, using a layer of the trained neural network, a residual value based on the proper subset of the received image and at least one corresponding image portion of a preceding lower resolution image in the video file and at least one corresponding image portion of a subsequent lower resolution image in the video file, upscale the lower-resolution image using bilinear upsampling, and combine the upscaled received image and residual value to generate an enhanced image.

Techniques for enhancing an image are described. For example, a lower-resolution image from a video file may be enhanced using a trained neural network applying the trained neural network to enhance a middle lower-resolution image of the plurality of lower-resolution images using a generator with filters of a generative adversary network according to the request by: temporally pre-processing the lower-resolution images by concatenating the lower-resolution images along a temporal dimension, temporally reducing the concatenated images, removing artifacts of the temporally reduced concatenated images at a first resolution to generate a first red, green, blue (RGB) image using an artifact removal layer and features of the first RGB image, processing features of the first RGB image at a second, higher resolution to generate a second RGB image, upsampling the features of the second RGB image, processing features of the upsampled second RGB image at a third, higher resolution to generate a third RGB image, upsampling the features of the third RGB image to generate a residual of the third RGB image, generating a filter from the features of the first RGB image, performing a product of the generated filter and the RGB image generated by the artifact removal layer, and summing the product with the residual of the third RGB image to generate an enhanced image

An image processing method and device, an electronic device and a computer-readable storage medium are provided. The method includes that: face recognition is performed on an image to be processed; responsive to detecting that the image to be processed includes a portrait, a shooting distance of the portrait is acquired; responsive to determining that the shooting distance meets a preset distance condition, a parameter relationship matched with the met distance condition is acquired; a beauty parameter corresponding to the shooting distance is selected according to the parameter relationship; and beauty processing is performed on the portrait according to the beauty parameter.

The present disclosure provides a watermark image processing method and apparatus, a device and a computer readable storage medium. In the embodiments of the present disclosure, it is feasible to obtain at least one similar image approximate to the watermark image according to the watermark image including the watermark, and obtain a replaceable image of each similar image of said at least one similar image in the watermark area, according to a watermark area where the watermark is located in the watermark image so that it is possible to obtain a carrier image not including the watermark, according to the watermark image and the replaceable image of said each similar image in the watermark area. Since the replaceable image of the similar image in the watermark area is employed to obtain the carrier image not including the watermark, the valid content in the watermark image covered by the watermark is restored and thereby the reliability of the image is improved.

Techniques to improve the quality of captured images by reducing the effects of undesired objects (e.g., screen glare) are disclosed. The techniques may involve the use of face detection to localize the likely position of screen glare within the captured images (e.g., on a user's eyeglasses), as well as an awareness of the content that is being displayed on a display screen (or other light-projecting element projecting light into the scene) at the moment of capture of the respective image. The techniques may then model the position, size, and/or distortion of the screen contents (or other projected light) reflected by the user's eyeglasses (or other reflective surface in the captured scene environment). Once the appearance of the undesired screen glare has been modeled in the captured image, the techniques may perform an image modification operation to remove or reduce the undesired glare from the originally-acquired image in an efficient manner.

Systems and methods for removing objects from images are disclosed. An image processing application identifies a boundary of each object of a set of objects in an image. In some cases, the identification uses deep learning. The image processing application identifies a completed boundary for each object of the set of objects by providing the object to a trained model. The image processing application determines a set of masks. Each mask corresponds to an object of the set of objects and represents a region of the image defined by an intersection of the boundary of the object and the boundary of a target object to be removed from the image. The image processing application updates each mask by separately performing content filling on the corresponding region. The image processing application creates an output image by merging each of the updated masks with portions of the image.