Abstract: An image display apparatus comprises at least one memory storing instructions, and at least one processor configured to execute the instructions to acquire a plurality of pieces of image data from a camera, identify a person from the image data, estimate a possibility of the person identified from the image data having developed an infectious disease, detect an image of interest including a person of interest regarding which there is the possibility of the person of interest having developed an infectious disease and a nearby person present in the vicinity of the person of interest based on a result of the estimation, extract a series of images including the image of interest, and display the extracted series of images.

Abstract: A computer implemented method includes receiving, from a remote system, object data comprising values of a set of adjustable parameters of a respective object representation model for each object of a plurality of objects and compositing data indicating at least a respective trajectory of each of the plurality of objects relative to a reference frame. The method includes processing the object data and the compositing data using the respective object representation models to generate output video data depicting a scene including an animated representation of each object of the plurality of objects following the respective trajectory relative to the reference frame. For each object of the plurality of objects, the respective object representation model comprises a respective neural network and is arranged to generate, using the respective neural network, animated representations of the object in which a geometry the object is controllable by the set of adjustable parameters.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating three-dimensional meshes representing two-dimensional images for editing the two-dimensional images. The disclosed system utilizes a first neural network to determine density values of pixels of a two-dimensional image based on estimated disparity. The disclosed system samples points in the two-dimensional image according to the density values and generates a tessellation based on the sampled points. The disclosed system utilizes a second neural network to estimate camera parameters and modify the three-dimensional mesh based on the estimated camera parameters of the pixels of the two-dimensional image. In one or more additional embodiments, the disclosed system generates a three-dimensional mesh to modify a two-dimensional image according to a displacement input.

Abstract: An apparatus includes an extraction unit configured to extract an N-dimensional feature vector (N is an integer that is greater than M) in a second format including an M-dimensional feature vector (M is an integer of 2 or greater) in a first format from input data, and an identification unit configured to identify a target in the input data based on the feature vector in the first format and the feature vector in the second format.

Abstract: In a next-generation retail store, the presence of a shopper at a particular shelf location, at about the time that an item was removed from that shelf location, gives rise to a hypothesis that the item may have been picked for purchase by that shopper. An ensemble of different such hypotheses, about different items removed by different shoppers, is evaluated jointly to determine which hypotheses are most likely. Other factors can influence the determinations, such as a physical distance between picked products, together with a time interval between their picking. If cameras are used to detect removal of items from shelves, hand depictions captured by such cameras are further factors that may be considered, e.g., helping associate certain item removals with a common shopper. By generating purchase lists for each shopper with such methods, shoppers can be relieved of the need of having each item scanned at a checkout.

Abstract: A detection result output method, an electronic device, and a medium are provided. The detection result output method includes: obtaining first image information of a first object, where the first image information includes skin information of the first object; outputting a target detection result in a case that a matching degree between a first image and a target image meets a first preset condition; and outputting a first detection result in a case that the matching degree between the first image and the target image does not meet the first preset condition. The target detection result is a detection result corresponding to the target image, and the first detection result is a detection result corresponding to the first image.

Abstract: A face authentication apparatus includes: an acquisition unit that acquires face image data of a person from image capturing apparatuses, a determination unit that determines whether registration data, having degree of matching with the face image data that is equal to or more than a threshold value, is registered in a storage device, a prompting unit that prompts the person to input identifying information when the determination unit determines that the registration data is not registered in the storage device, a reception unit that receives the identifying information input, a registration after input reception unit that registers the face image data as registration data in the storage device when the reception unit successfully receives an input of the identifying information, and a setting unit that sets a threshold value, to be used by the determination unit, in association with the registration data registered by the registration after input reception unit.

Abstract: Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.

Abstract: A photographing method and an electronic device are provided. The method includes: receiving a first input; starting first photographing in response to the first input; receiving a second input; and in response to the second input, starting second photographing in a case that it is determined that a photographing application obtains target image data of the first photographing from an operating system, and processing the target image data by using a first preset algorithm, to obtain a first processing result. The target image data is initial image data outputted through a sensor of a camera, or target image data is image data outputted after format conversion is performed on the initial image data. The first preset algorithm is an algorithm corresponding to the target image data. The method further includes performing encoding based on the first processing result to obtain a first photographic image.

Abstract: A computer system is configured to remove motion artifacts in medical images using a generative adversarial network (GAN). The computer system instantiates the GAN having one or more generative network(s) and one or more discriminative network(s) that are pitted against each other to train a generative model and a discriminative model. The training uses a training dataset including a plurality of medical images that are previously classified as without significant motion artifacts for diagnostic purposes. The discriminative model is trained to classify medical images as real or artificial. The generative model is trained to enhance the quality of a medical image and remove motion artifacts by producing a medical image directly from a post-contrast image, without using a pre-contrast mask.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for objection classification. One of the methods includes: obtaining a first set of images of objects that have a likelihood of being at a property that satisfies a likelihood threshold; generating, for each object, a binary classifier from a set of images of the respective object; determining, using at least one of the binary classifiers, that an image of an unknown object was classified as an object from the objects; in response to determining, using the binary classifiers, that the image of the unknown object was classified as an object from the objects, selecting a second set of images of unknown objects that does not include the image; and generating a multiclass classifier for use classifying objects using i) the first set as respective classes and ii) the second set that does not include the image.

Abstract: An object detection device has a controller configured to receive classification data and regions for an image. The regions are prioritized and if a region is selected for further prediction, a photographic feature for the selected region is determined and a re-capture of the selected region is made based on the photographic feature by updating an image capturing device. The re-captured region is re-processed and classification data is re-generated. Then, final object detection for selected region(s) is performed and final object detection for not-selected region(s) is performed.

Abstract: An image processing method includes acquiring a first image that represents an object, a second image that represents the object and is different from the first image in imaging condition, and identification information for identifying the object; extracting a feature amount from the second image by using an extractor; classifying the object by using the feature amount and a classifier; restoring by generating a restored image close to the first image from the second image, using the feature amount and a generator; and training the extractor and the generator such that values corresponding to a first difference between a result of classification of the object and the identification information and a second difference between the restored image and the first image become small.

Abstract: A method for intelligently sharing a content by an electronic device is provided. The method includes determining, by the electronic device, a context of sharing the content. The method includes analyzing, by the electronic device, the content with reference to the context. The method includes identifying, by the electronic device, portions of the content as non-shareable based on the analysis. The method includes providing, by the electronic device, a modification action suggestion on the portions identified as non-shareable.

Abstract: In an embodiment, a virtual reality ride system includes a display to present virtual reality image content to a first rider, an audio sensor to capture audio data associated with a second rider, and an image sensor to capture image data associated with the second rider. The virtual reality ride system also includes at least one processor communicatively coupled to the display and configured to (i) receive the audio data, the image data, or both, (ii) generate a virtual avatar corresponding to the second rider, wherein the virtual avatar includes a set of facial features, (iii) update the set of facial features based on the audio data, the image data, or both, and (iv) instruct the display to present the virtual reality image content including the virtual avatar and the updated set of facial features.

Abstract: The present disclosure generally pertains to a polarization imaging portion having a plurality of imaging elements, wherein each imaging element is configured to convert light into an electric signal, the polarization imaging portion further including: a set of event sensors configured to detect an event being indicative of an intensity change of the light; a set of polarization filters; and a set of tunable polarizers configured to adjust a polarization of the light in response to an electric signal, wherein each polarization filter of the set of polarization filters is associated with a respective tunable polarizer of the set of tunable polarizers, thereby configuring a set of tunable polarization filters, such that the set of tunable polarization filters is associated with the set of event sensors.

Abstract: Disclosed is an image segmentation method, including: obtaining an original image to be segmented; preprocessing the original image to be segmented, comprising, by taking each candidate sampling start point as an actual sampling start point, down-sampling the original image to be segmented, and obtaining down-sampled images corresponding to each candidate sampling start point; and inputting preprocessed images into a trained segmentation model to obtain an object segmented image corresponding to the original image.

Abstract: A method by one or more network devices executing one or more smart contracts stored in a blockchain for anonymizing faces appearing in digital media content. The method includes obtaining, for each of a plurality of users, a facial model associated with that user, obtaining digital media content digital media content, determining whether that detected face matches the face of any of the plurality of users based on applying one or more of the facial models associated with the plurality of users to that detected face, anonymizing that detected face to generate an anonymized face in response to a determination that that detected face matches the face of one of the plurality of users, and providing the anonymized face to the media platform.

Abstract: Embodiments of this application disclose a focusing method and an electronic device, including: In response to a first operation, an electronic device starts photographing, and displays a first interface. The electronic device displays a Kth frame of preview image in the first interface at a first moment. The Kth frame of preview image is collected by the camera by using a face of a first target as a first focusing frame, and the face of the first target meets a preset facial recognition condition in the Kth frame of preview image. The electronic device displays an Mth frame of preview image in the first interface at a second moment. The Mth frame of preview image is obtained by the camera by focusing on the first focusing frame, the face of the first target does not meet the preset facial recognition condition in the Mth frame of preview image.

Abstract: An information processing apparatus (10) includes a time and space information acquisition unit (110) that acquires high-risk time and space information indicating a spatial region with an increased possibility of an accident occurring or of a crime being committed and a corresponding time slot, a possible surveillance target acquisition unit (120) that identifies a video to be analyzed from among a plurality of videos generated by capturing an image of each of a plurality of places, on the basis of the high-risk time and space information, and analyzes the identified video to acquire information of a possible surveillance target, and a target time and space identification unit (130) that identifies at least one of a spatial region where surveillance is to be conducted which is at least a portion of the spatial region or a time slot when surveillance is to be conducted, from among the spatial region and the time slot indicated by the high-risk time and space information, on the basis of the information of the

Abstract: An example method includes identifying images of an individual and determining, based on the images, a facial feature of the individual. The example method further includes determining a contextual feature of the individual. Based on the facial feature and the contextual feature, an identity of the individual is determined.

Abstract: A facial verification method and apparatus is disclosed. The facial verification method includes detecting a face region in an input image, determining whether the detected face region represents a partial face, in response to a determination that the detected face region represents the partial face, generating a synthesized image by combining image information of the detected face region and reference image information, performing a verification operation with respect to the synthesized image and predetermined first registration information, and indicating whether facial verification of the input image is successful based on a result of the performed verification operation.

Abstract: A facial feature matching system comprises a facial feature matching engine. A first user selection of reference facial images is received, and facial features of reference faces are characterized using the facial feature recognition engine comprising a neural network with input, hidden, and output layers. The facial features are weighted. The weighted facial features are used to identify users that have facial features similar to the weighted facial features, wherein the respective reference faces include faces different than the faces of the users. Similarity indicators are generated for the identified users. The generated respective similarity indicators are used to generate a ordering of the identified users which is rendered via the user device. A first user selection of a second user in the ordered identified users is received and the first user and the second user are enabled to communicate over an electronic communication channel.

Abstract: A process and an activation device (30) provides a user (B) activation of a drug measuring device (100). This drug measuring device includes an input unit (3), a testing unit (6) for testing given samples and an image recording device (12). The activation device (30) receives an activation image set (InB), which was generated by the drug measuring device or by a drug measuring device and at least one image (40, 40.1) from the image recording device. The received activation image set is checked as to meeting a predefined release criterion. For this the activation image set is compared with a predefined reference image set (35) for the user. If the release criterion is met, the drug measuring device is released for the user. An activation data set (32) for the user is completed by at least one image of the activation image set, which shows the user.

Abstract: An apparatus is described which includes two or more colour displays arranged to provide piece-wise continuous illumination of a volume, and one or more cameras arranged to image the volume. The apparatus is configured to control the colour displays and the cameras to illuminate the volume with each of two or more illumination conditions. The apparatus is also configured to obtain two or more sets of images, which include sufficient information for calculation of a reflectance map and a photometric normal map of an object or subject positioned within the volume. Each set of images is obtained during illumination of the volume with one or more corresponding illumination conditions. When viewed from the volume, the apparatus only provides direct illumination of the volume from angles within a zone of a hemisphere, which is less than a hemisphere.

Abstract: A method including receiving, at a camera, light comprising a visible spectrum and an infrared spectrum (200). The method also includes detecting, using the visible spectrum, a candidate image of a head (202). The method also includes determining an estimated true size of the head (204). The method also includes determining, using the infrared spectrum, a temperature of the head (206). The method also includes filtering the candidate image of the head with respect to an operation of a video controller configured to track one or more images of heads in the visible spectrum. Filtering is based on both the estimated true size of the head and the temperature of the head (208).

Abstract: Provided are a display apparatus and a method. The display apparatus includes a display, an interface component configured to connect with a rotatable camera and a controller. The controller is configured for: obtaining a reference image captured by the camera, where the reference image comprises one or more persons with one or more face patterns; extracting a tracking target area from the reference image according to a current imaging parameter of the camera, where the tracking target area is a regular-shaped area determined according to one or more weights for the one or more face patterns, the current imaging parameter of the camera comprises a focal length of the lens component of the camera; and sending a rotation instruction to the camera to adjust an orientation of the camera to cause the tracking target area locate in a middle area of an image presented on the display.

Abstract: The embodiments herein provide a secure computing resource set identification, evaluation, and management arrangement, employing in various embodiments some or all of the following highly reliable identity related means to establish, register, publish and securely employ user computing arrangement resources in satisfaction of user set target contextual purposes.

Abstract: An electronic device is provided. The electronic device includes a camera module, a display, and a processor configured to detect at least one piece of face recognition information based on a plurality of subjects included in an image received in a capture mode where a gaze recognition capturing function is activated, upon identifying a presence of at least two pieces of face recognition information mapped with gaze calibration information among the at least one piece of face recognition information, detect score information about the at least two pieces of face recognition information based on depth information and body information, determine that a subject corresponding to face recognition information including highest score information among the at least two pieces of face recognition information is a capturer, and if the determined capturer gazes at a capture button, perform a first image capturing function of displaying a captured image on the display.

Abstract: A method for classifying a detected object is disclosed. First and second object detectors detect first and second objects in first and second image frames, respectively, of a video sequence, and first and second probability scores respectively are calculated indicating a probability that the detected object belongs to a specific class. The second image frame is subsequent to the first image frame. The first object detector has a higher object detection precision and a longer processing time than the second object detector. The first and second object detections are performed in parallel. Reducing the first classification threshold or increasing the first probability score are performed if the first probability score is below a first classification threshold and the second probability score is above a second classification threshold. The first object is determined to belong to the specific class based on the probability scores and the classification thresholds.

Abstract: Disclosed herein are an apparatus and method for tracking a missing person based on attributes. The apparatus for tracking a missing person based on attributes according to an embodiment of the present disclosure includes memory in which at least one program is recorded and a processor for executing the program. The program may perform receiving a missing person report including missing situation information and attribute information representing appearance of a missing person, acquiring CCTV video based on the missing situation information, extracting full-body image candidates assumed to be of the missing person, among the full-body images of human objects in the CCTV video, based on the attribute information, receiving a selection for one of the extracted full-body image candidates as the full-body image of the missing person, and tracking the travel path of the missing person by analyzing CCTV video based on the selected full-body image of the missing person.

Abstract: Various embodiments described herein provide techniques for analyzing an image (e.g., a selfie) of a user with one or more pre-trained machine learned models, to detect facial characteristics of the user. Then, using the output of the machine learned model(s), various combinations of detected facial characteristics are used to assign the user with one style profile of several predefined style profiles. Finally, the style profile may be used in the selection of one or more products to be recommended to the user.

Abstract: An information processing apparatus that displays a captured image captured by an imaging apparatus on a display unit, the information processing apparatus includes a display controller configured to perform display control to display an image of a region of interest included in the captured image, on the display unit, wherein, the display controller displays, in a case where the region of interest is in an angle of view of a frame of the captured image, the image of the region of interest included in the frame, and displays, in a case where the region of interest is off from the angle of view of the frame of the captured image, the image of the region of interest included in a preceding frame preceding the frame.

Abstract: Methods and systems are disclosed for generating AR experiences on a messaging platform. The methods and systems perform operations including: detecting a real-world object depicted in a first image captured by a first camera of a client device, the client device comprising a second camera; extracting one or more textures from the real-world object depicted in the first image; selecting a target object depicted in a second image captured by the second camera, the second image being captured by the second camera simultaneously with the first image captured by the first camera; generating an augmented reality (AR) element comprising the target object modified based on the one or more textures extracted from the real-world object depicted in the first image; and causing display of the AR element within the second image.

Abstract: A computer-implemented method of changing a face within an output image or video frame that includes: receiving an input image that includes a face presenting a facial expression in a pose; processing the image with a neural network encoder to generate a latent space point that is an encoded representation of the image; decoding the latent space point to generate an initial output image in accordance with a desired facial identity but with the facial expression and pose of the face in the input image; identifying a feature of the facial expression in the initial output image to edit; applying an adjustment vector to a latent space point corresponding to the initial output image to generate an adjusted latent space point; and decoding the adjusted latent space point to generate an adjusted output image in accordance with the desired facial identity but with the facial expression and pose of the face in the input image altered in accordance with the adjustment vector.

Abstract: A search apparatus for searching media data for a target region that matches query data includes a first feature extraction unit configured to extract a first feature vector from the query data using a first trained neural network; a second feature extraction unit configured to obtain a first region from the media data and extract a second feature vector from the first region using a second trained neural network; a localization unit configured to determine a candidate for the target region using a third trained neural network, based on the first feature vector, the second feature vector, and the first region or a location of the first region; and a control unit configured to repeat the operations of the second feature extraction unit and the localization unit until a predetermined condition is satisfied, by using the determined candidate for the target region as the first region to be used by the second feature extraction unit.

Abstract: An information processing apparatus (10) includes a time and space information acquisition unit (110) that acquires high-risk time and space information indicating a spatial region with an increased possibility of an accident occurring or of a crime being committed and a corresponding time slot, a possible surveillance target acquisition unit (120) that identifies a video to be analyzed from among a plurality of videos generated by capturing an image of each of a plurality of places, on the basis of the high-risk time and space information, and analyzes the identified video to acquire information of a possible surveillance target, and a target time and space identification unit (130) that identifies at least one of a spatial region where surveillance is to be conducted which is at least a portion of the spatial region or a time slot when surveillance is to be conducted, from among the spatial region and the time slot indicated by the high-risk time and space information, on the basis of the information of the

Abstract: Systems and methods are described for generating pixel image data, using a lensless camera, based on light that travels through a mask that with pattern masking the lensless camera. The system applies a transformation function to the pixel image data to generate frequency domain image data. The system inputs the frequency domain image data into a machine learning model, wherein the machine learning model does not have access to data that represents the pattern of the mask. The model is trained using a set of images with the feature that are captured by the flat, lensless camera through the mask. The system processes the frequency domain image data using the machine learning model to determine whether the pixel image data depicts the image feature. The system further performs an action based on determining that the pixel image data depicts the image feature.

Abstract: A user authentication system comprising one or more cloud server computers storing a user database storing user data associated with a user account and one or more corresponding user graphical representations, and a facial scanning and authentication module connected to the database. The one or more cloud server computers are configured to authenticate a user by performing a facial scanning of the user, including extracting facial feature data from camera data received from a client device and checking the extracted facial feature data for a match against a user graphical representation associated with the user account in the user database. If a matching user graphical representation is found in the checking step, the system provides the user with access to the corresponding user account. Otherwise, the system generates, from the camera data, a new user graphical representation along with a new user account stored in the user database.

Abstract: A remote signal-based method and system of performing an authentication of images of a person in order to permit access to a secured resource. The system and method are configured to cause a visual and/or haptic pattern response to occur in a secondary device while collecting image data from a different, primary device. The image data is evaluated to determine whether the appropriate pattern is present. If the pattern is present, the system determines the image is authentic and can verify an identity of the person, and can further be configured to automatically grant the person access to one or more services, features, or information for which he or she is authorized.

Abstract: A method of testing an impedance-sensitive system with a switching device, wherein the method comprises: switching the disconnecting device into the on-state configured to permit transmission of energy via the coil; implementing a first measurement with the impedance-sensitive system; switching the disconnecting device into the off-state configured to permit damping of the external positioning signal that couples into the coil so as to reduce the undesirable oscillations of the coil; implementing a second measurement with the impedance-sensitive system; performing a comparison of the first measurement and the second measurement; performing a verification of the comparison with a target specification; and displaying a correct function and/or a malfunction depending on the verification.

Abstract: The present disclosure provides method and apparatus for automatically generating a training data set for object recognition. Profile information of a plurality of objects may be obtained. For each object among the plurality of objects, a group of initial images associated with the object may be collected based on identity information of the object included in profile information of the object. The group of initial images may be filtered to obtain a group of filtered images associated with the object. A group of training data pairs corresponding to the object may be generated through labeling each of the group of filtered images with the identity information of the object. The group of training data pairs may be added into the training data set.

Abstract: A photographing control device includes a storage unit that stores identification information of a plurality of persons as a group, an acquiring unit that acquires a photographed image obtained by a predetermined photographing device and capturing multiple persons, a region identifying unit that identifies a plurality of facial regions from the photographed image, an individual authentication controlling unit that causes an authentication device storing a set of facial feature information items of the plurality of persons to perform facial authentication of each of the identified facial regions by use of the set of facial feature information items, and an output unit that outputs the photographed image as an output image if facial authentication of each of the facial feature information items of the respective persons belonging to the group has succeeded with regard to any one of the plurality of facial regions.

Abstract: The present invention provides a travel control apparatus (20) including an in-vehicle image acquisition unit (21) that acquires an in-vehicle image generated by a camera for capturing an inside of a vehicle compartment of a reserved vehicle, an in-vehicle sensing unit (22) that senses that a reserving person is present within a vehicle compartment of the reserved vehicle, based on the in-vehicle image, and a permission output unit (23) that outputs, when it is sensed that the reserving person is present within a vehicle compartment of the reserved vehicle, travel permission of the reserved vehicle.

Abstract: A method for creating a non-riggable model of a face of a person, the method includes obtaining video and depth information regarding the face of the person, wherein different images of the video are acquired by a camera at different camera locations; and for each image of the different images repeating the steps of: separating face information from background information; determining translation and rotation parameters that represent the different camera locations; and generating the non-riggable model of the face of the person based on the face information and the translation and rotation parameters.

Abstract: An image processing device combines a plurality of time-series images to generate a composite image with a higher resolution than a resolution of the plurality of images. The image processing device includes a processor that includes hardware and that is configured to: detect depth information of at least one image of the plurality of images; and set the number of images to be combined for generating the composite image on the basis of the detected depth information. The depth information indicates a depth of a captured scene of the at least one image. The processor is configured to reduce the number of images as the depth of the captured scene increases.

Abstract: An image processing method includes: acquiring image data; detecting a face region including at least a part of a face of a person from the image data; setting a first region used for detection of an eye of the person in the face region having been detected; setting a second region estimated to include a pupil or an iris by narrowing the first region based on a predetermined criterion; detecting pupil information indicating the pupil or the iris in the second region; and outputting the pupil information having been detected.

Abstract: Using a first trained residual neural network, an event analysis is generated from a set of event description encodings, an event description encoding in the set of event description encodings encoding a natural language description of an event, the event analysis comprising a first set of coordinates in an event space. Using a second trained residual neural network, the event analysis and a user description encoding, a personalization analysis is generated, the user description encoding a user interaction with the event, the personalization analysis comprising a component of a second set of coordinates in the event space. Using a combination of the event analysis and the personalization analysis, a first event component is activated, the first event component comprising a component of the event.

Abstract: The embodiments herein provide a system and method for personalized cartoon image generation. The method (100) comprises launching a keyboard interface (101), capturing a digital picture (102), face segmentation using neural network (103), normalization of segmented face (104), face cartoonification (105), which generates bobble head, facial landmark extraction (106), facial expression feature transfer (109) and customization of the generated plurality of cartoon images (110). Hence, the embodiments herein helps in creation of personalized plurality of cartoon images to make the user part of the conversations and the graphics or content shared look similar to the user input face and more aesthetically pleasing instead of using any reference stickers to convey the messages.

Abstract: An image processing apparatus includes at least one processor or circuit configured to execute a plurality of tasks including an acquisition task configured to acquire two first images made by capturing the same object at two different viewpoints, and an image processing task configured to input the two first images into a machine learning model and to estimate a second image at one or more viewpoints different from the two viewpoints.