Abstract: Embodiments described herein provide a system for generating synthetic images with localized editing. During operation, the system obtains a source image and a target image for image synthesis and selects a semantic element from the source image. The semantic element indicates a semantically meaningful part of an object depicted in the source image. The system then determines the style information associated with the source and target images. Subsequently, the system generates a synthetic image by transferring the style of the semantic element from the source image to the target image based on the feature representations. In this way, the system can facilitate localized editing of the target image.

Abstract: Embodiments described herein provide a system for localized contextual video annotation. During operation, the system can segment a video into a plurality of segments based on a segmentation unit and parse a respective segment for generating multiple input modalities for the segment. A respective input modality can indicate a form of content in the segment. The system can then classify the segment into a set of semantic classes based on the input modalities and determine an annotation for the segment based on the set of semantic classes.

Abstract: A method of generating an image from multiple cameras having different focal lengths is described. The method comprising receiving a wide image and a tele image; aligning the wide image and the tele image to overlap a common field of view; correcting for photometric differences between the wide image and the tele image; selecting a stitching seam for the wide image and the tele image; and joining the wide image and the tele image to generate a composite image, wherein a first portion of the composite image on one side of the stitching seam is from the wide image and a second portion of the composite image on the other side of the stitching seam is from the tele image. An electronic device for generating an image is also described.

Abstract: A method operates a three-dimensional (3D) metal object manufacturing system to compensate for displacement errors that occur during object formation. In the method, image data of a metal object being formed by the 3D metal object manufacturing system is generated prior to completion of the metal object and compared to original 3D object design data of the object to identify one or more displacement errors. For the displacement errors outside a predetermined difference range, the method modifies machine-ready instructions for forming metal object layers not yet formed to compensate for the identified displacement errors and operates the 3D metal object manufacturing system using the modified machine-ready instructions.

Abstract: One embodiment can provide a system for detecting outlines of objects in images. During operation, the system receives an image that includes at least one object, generates a random noise signal, and provides the received image and the random noise signal to a shape-regressor module, which applies a shape-regression model to predict a shape outline of an object within the received image.

Abstract: A method for curvilinear object segmentation includes receiving at least one input image comprising curvilinear features. The at least one image is mapped, using a processor, to output segmentation maps using a deep network having a representation module and a task module. The mapping includes transforming the input image in the representation module using learnable filters trained to suppress noise in one or more of a domain and a task of the at least one input image. The segmentation maps are produced using the transformed input image in the task module.

Abstract: A method for curvilinear object segmentation includes receiving at least one input image comprising curvilinear features. The at least one input image is mapped to segmentation maps of the curvilinear features using a deep network having a representation module and a task module. The mapping includes transforming the input image in the representation module using learnable filters configured to balance recognition of curvilinear geometry with reduction of training error. The segmentation maps are produced using the transformed input image in the task module.

Abstract: An electronic device, method, and computer readable medium for multi-frame image processing using semantic saliency are provided. The electronic device includes a camera, a display, and a processor. The processor is coupled to the camera and the display. The processor receives a plurality of frames captured by the camera during a capture event; identifies a salient region in each of the plurality of frames; determines a reference frame from the plurality of frames based on the identified salient regions; fuses non-reference frames with the determined reference frame into a completed image output.

Abstract: A system is provided for generating a custom article to fit a target surface. During operation, the system compares an input dataset with a number of cut template cut meshes. A respective cut template cut mesh includes one or more cutting paths that correspond to a boundary of the mesh. Next, the system identifies a template cut mesh that produces a closest match with the input dataset, and applies global geometric transformations to the identified template cut mesh to warp the template cut mesh to conform to the input dataset. The system further refines and projects a set of boundary and landmark points from the template cut mesh to the input dataset to define cutting paths for the input dataset. Next, the system applies cutting paths to the input dataset to produce a cut-and-trimmed mesh.

Abstract: A method for predicting the realism of an object within an image includes generating a training image set for a predetermined object type. The training image set comprises one or more training images at least partially generated using a computer. A pixel level training spatial realism map is generated for each training image of the one or more training images. Each training spatial realism map configured to represent a perceptual realism of the corresponding training image. A predictor is trained using the training image set and the corresponding training spatial realism maps. An image of the predetermined object is received. A spatial realism map of the received image is produced using the trained predictor.

Abstract: One embodiment can provide a system for detecting outlines of objects in images. During operation, the system receives an image that includes at least one object, generates a random noise signal, and provides the received image and the random noise signal to a shape-regressor module, which applies a shape-regression model to predict a shape outline of an object within the received image.

Abstract: A method for curvilinear object segmentation includes receiving at least one input image comprising curvilinear features. The at least one input image is mapped to segmentation maps of the curvilinear features using a deep network having a representation module and a task module. The mapping includes transforming the input image in the representation module using learnable filters configured to balance recognition of curvilinear geometry with reduction of training error. The segmentation maps are produced using the transformed input image in the task module.

Abstract: A method for curvilinear object segmentation includes receiving at least one input image comprising curvilinear features. The at least one image is mapped, using a processor, to output segmentation maps using a deep network having a representation module and a task module. The mapping includes transforming the input image in the representation module using learnable filters trained to suppress noise in one or more of a domain and a task of the at least one input image. The segmentation maps are produced using the transformed input image in the task module.

Abstract: A system creates an electronic file corresponding to a printed artifact by launching a video capture module that causes a mobile electronic device to capture a video of a scene that includes the printed artifact. The system analyzes image frames in the video in real time as the video is captured to identify a suitable instance. In one example, the suitable instance is a frame or sequence of frames that contain an image of a page or side of the printed artifact and that do not exhibit a page-turn event. In response to identification of the suitable instance, the system will automatically cause a photo capture module of the device to capture a still image of the printed artifact. The still image has a resolution that is higher than that of the image frames in the video. The system will save the captured still images to a computer-readable file.

Abstract: Embodiments described herein provide a system for generating semantically accurate synthetic images. During operation, the system generates a first synthetic image using a first artificial intelligence (AI) model and presents the first synthetic image in a user interface. The user interface allows a user to identify image units of the first synthetic image that are semantically irregular. The system then obtains semantic information for the semantically irregular image units from the user via the user interface and generates a second synthetic image using a second AI model based on the semantic information. The second synthetic image can be an improved image compared to the first synthetic image.

Abstract: A method, non-transitory computer readable medium and apparatus for generating graphical chromophore maps are disclosed. For example, the method includes receiving an image of a customer from a mobile endpoint device of the customer, wherein the image is taken via the mobile endpoint device of the customer, converting RGB values of the image into a spectral representation, performing a constrained independent component analysis (ICA) on the spectral representation to obtain three or more independent components that are ordered, generating a first graphical chromophore map of a first independent component of the three or more independent components that are ordered and a second graphical chromophore map of a second independent component of the three or more independent components that are ordered and transmitting the first graphical chromophore map and the second graphical chromophore map to the mobile endpoint device of the customer for display.

Abstract: A mobile electronic device processes a sequence of images to identify and re-identify an object of interest in the sequence. An image sensor of the device, receives a sequence of images. The device detects an object in a first image as well as positional parameters of the device that correspond to the object in the first image. The device determines a range of positional parameters within which the object may appear in a field of view of the device. When the device detects that the object of interest exited the field of view it subsequently uses motion sensor data to determine that the object of interest has likely re-entered the field of view, it will analyze the current frame to confirm that the object of interest has re-entered the field of view.

Abstract: One embodiment facilitates generating synthetic data objects using a semi-supervised GAN. During operation, a generator module synthesizes a data object derived from a noise vector and an attribute label. The system passes, to an unsupervised discriminator module, the data object and a set of training objects which are obtained from a training data set. The unsupervised discriminator module calculates: a value indicating a probability that the data object is real; and a latent feature representation of the data object. The system passes the latent feature representation and the attribute label to a supervised discriminator module. The supervised discriminator module calculates a value indicating a probability that the attribute label given the data object is real. The system performs the aforementioned steps iteratively until the generator module produces data objects with a given attribute label which the unsupervised and supervised discriminator modules can no longer identify as fake.

Abstract: A method, non-transitory computer readable medium and apparatus for determining spectral characteristics of an image captured by a camera on a mobile endpoint device are disclosed. For example, the method includes receiving the image of a color calibration card comprising a plurality of color patches and a quick response (QR) code, wherein each one of the plurality of color patches has a known spectral reflectance, determining spectral characteristics from the image of the color calibration card, wherein the spectral characteristics are used to analyze additional images that are received from the camera on the mobile endpoint device and transmitting an activation signal to activate an incentive associated with the QR code to the mobile endpoint device in response to receiving the image of the color calibration card.

Abstract: A method, non-transitory computer readable medium and apparatus for transmitting an assessment of facial skin health of a customer are disclosed. For example, the method includes receiving an image of a customer from a mobile endpoint device of the customer, analyzing one or more parameters of a facial skin of the customer in the image of the customer, determining the assessment of facial skin health of the customer based on the one or more parameters of the facial skin that are analyzed and transmitting the assessment of facial skin health to the mobile endpoint device of the customer to cause the mobile endpoint device to automatically display the assessment of facial skin health.