Abstract: An eye tracking device for tracking an eye is described. The eye tracking device comprises: a first diffractive optical element, DOE, arranged in front of the eye, an image module, wherein the image module is configured to capture an image of the eye via the first DOE. The first DOE is adapted to direct a first portion of incident light reflected from the eye, towards the image module. The eye tracking device is characterized in that the first DOE is configured to provide a lens effect.

Abstract: A computer-implemented method for guiding a user in calibrating a wearable eye tracking device is disclosed. The method comprises determining a calibration point and an initial gaze point of a user wearing the eye tracking device. The method further comprises displaying a calibration marker on a remote display device at the initial gaze point, wherein the calibration marker is configured to indicate a direction. The method further comprises, in response to a movement of the gaze point in relation to the calibration point caused by movement of the user's head and/or movement of the remote display device, determining a current gaze point, and updating the calibration marker in accordance with a calculated direction and/or the distance from the current gaze point to the calibration point.

Abstract: Techniques for using a deep generative model to generate synthetic data sets that can be used to boost the performance of a discriminative model are described. In an example, an autoencoding generative adversarial network (AEGAN) is trained to generate the synthetic data sets. The AEGAN includes an autoencoding network and a generative adversarial network (GAN) that share a generator. The generator learns how to the generate synthetic data sets based on a data distribution from a latent space. Upon training the AEGAN, the generator generates the synthetic data sets. In turn, the synthetic data sets are used to train a predictive model, such as a convolutional neural network for gaze prediction.

Abstract: The invention is related to a method and arrangement for calibrating the camera of an eye tracking device and compensate for a potential angular offset of the camera. The method comprises: the steps of capturing an eye image of a user, wherein the eye image contains a plurality of glints created by a plurality of illuminators in the eye tracking system; detecting glints in the eye image; projecting illuminator positions onto the eye image to determine expected glint positions; determining an angular offset between expected glint positions and detected glint positions for corresponding pairs of expected and detected glint positions; determining the angular correction for the eye tracking camera using the determined angular offset angle; and applying the angular correction for the eye tracking camera to an eye tracker camera model.

Abstract: Systems and methods for avatar eye animation is provided. The method include obtaining a first gaze vector of a user associated with a first eye of the user and obtaining a second gaze vector of the user associated with a second eye of the user. The method further includes determining a first point in a three-dimensional (3D) virtual space that the user is looking toward. The method also includes creating a second point in the 3D virtual space corresponding to the first point in the 3D virtual space. The method then includes rendering a first eye and a second eye of an avatar of the user in the 3D virtual space based on the second point in the 3D virtual space such that the first eye and the second eye of the avatar are looking toward the second point in the 3D virtual space.

Abstract: A method performed by a computer for generating a video comprising blink data of a user viewing a scene depicted as video data, where the blink data is overlayed on the video data. The method includes receiving sensor data. The sensor data includes at least the video data including at least one video frame, and gaze tracking data at least indicative of viewed positions within the scene depicted by at least one video frame of the video data. The method includes processing the sensor data to generate blink data indicative of blink motion of at least one eye of the user. The method includes generating a video overlay by rendering the blink data. generating an output video by mixing the video data and the video overlay.

Abstract: Techniques for controlling light sources used in eye tracking are described. In an example, an eye tracking system generates a first image and a second image showing at least a portion of the user eye illuminated by a predetermined set of illuminators of the eye tracking system. The eye tracking system determines a first position of a glint in the first image and a second position of the glint in the second image. Each of the first position and the second position is relative to a pupil edge. The eye tracking system predicts a third position of the glint relative to the pupil edge based on the first position and the second position. Further, the eye tracking system determines, from the predetermined set, an illuminator that corresponds to the glint and determines, based on the third position, whether to power off the illuminator to generate a third image of at least the portion of the user eye.

Abstract: There is provided mechanisms for calibration of an eye tracking system. An eye tracking system comprises a pupil centre corneal reflection (PCCR) based eye tracker and a non-PCCR based eye tracker. A method comprises obtaining at least one first eye position of a subject by applying the PCCR based eye tracker on an image set depicting the subject. The method comprises calibrating a head model of the non-PCCR based eye tracker, as applied on the image set, for the subject using the obtained at least one first eye position from the PCCR based eye tracker as ground truth. The head model comprises facial features that include at least one second eye position. The calibrating involves positioning the head model in order for its at least one second eye position to be consistent with the at least one first eye position given by the PCCR based eye tracker.

Abstract: A method of forming a polymer is disclosed. The method comprises: positioning a mould in relation to a bath containing a molten material to form a mould cavity between the mould and the molten material; adding a monomer within the mould cavity; and curing the monomer to form a polymer.

Abstract: A method of controlling exposure time is disclosed comprising receiving an image of an eye from an image sensor, the image resulting from the image sensor detecting light during a first exposure time. A pupil intensity is determined as an intensity of a representation of a pupil of the eye in the image and an iris intensity is determined as an intensity of a representation of an iris of the eye in the image. Furthermore, a pupil-iris contrast is determined as a contrast between the representation of the pupil in the image and the representation of the iris in the image. On a condition that the pupil intensity is determined to meet an intensity condition, an intensity compensated exposure time is determined which is different from the first exposure time, and on a condition that the pupil-iris contrast is determined to meet a contrast condition, a contrast compensated exposure time is determined which is different from the first exposure time.

Abstract: The present disclosure generally relates to the field of eye tracking systems. An eye tracking system is provided. The eye tracking system comprises an illuminator arrangement, including at least one light source, configured to illuminate an eye of a user. The eye tracking system is configured to enable a reduction of reflections from an optic arrangement (e.g., a pair of glasses) that is located in a light beam path between the illuminator arrangement and the eye when the eye tracking system is in use. The illuminator arrangement is configured to emit p-polarized light to be incident on a surface of the optic arrangement at an angle corresponding to, or substantially corresponding to, Brewster's angle.

Abstract: A user monitoring system receives a first data stream from a first recording device and a second data stream from a second recording device. Each of the first data stream and the second data stream include data relating to an eye of the user. The first data stream and the second data stream overlap temporally. The system processes the first data stream to determine a first blink sequence of the user, processes the second data stream to determine a second blink sequence of the user, and compares the first blink sequence and the second blink sequence to detect a blink pattern present in both the first blink sequence and the second blink sequence. The system determines a temporal offset of the first data stream and the second data stream by comparing respective positions of the blink pattern in the first data stream and the second data stream.

Abstract: The invention is related to a method and system for calibrating an eye tracking device configured to track a gaze point of a user on a display The method comprises: presenting a video on the display to a user, the video having a start size and a start position; tracking the gaze of the user, using an image sensor of the eye tracking device; and sequentially completing, for at least one calibration position, the steps of: resizing the video to a calibration size, wherein the calibration size is smaller than the start size, and translating the video to a calibration position; recording calibration data, using the eye tracking device, for the user viewing the video in the calibration position; and resizing the video to a second size that is greater than the start size.

Abstract: A method for training an eye tracking model is disclosed, as well as a corresponding system and storage medium. The eye tracking model is adapted to predict eye tracking data based on sensor data from a first eye tracking sensor. The method comprises receiving sensor data obtained by the first eye tracking sensor at a time instance and receiving reference eye tracking data for the time instance generated by an eye tracking system comprising a second eye tracking sensor. The reference eye tracking data is generated by the eye tracking system based on sensor data obtained by the second eye tracking sensor at the time instance. The method comprises training the eye tracking model based on the sensor data obtained by the first eye tracking sensor at the time instance and the generated reference eye tracking data.

Abstract: A system, a head-mounted device, a computer program, a carrier, and a method for a head-mounted device comprising an eye tracking sensor, for updating an eye tracking model in relation to an eye are disclosed. First sensor data in relation to the eye are obtained by means of the eye tracking sensor. After obtaining the first sensor data, the eye tracking sensor is moved in relation to the eye. After moving the eye tracking sensor, second sensor data in relation to the eye are obtained by means of the eye tracking sensor. The eye tracking model in relation to the eye is then updated based on the first sensor data and the second sensor data.

Abstract: A method for processing a gaze signal in an eye tracking system is provided. The method comprises receiving a first image of a user's eye captured at a first point in time and a second image of the users eye captured at a second point in time subsequent to the first point in time, and determining, based on the first image and the second image, whether eye movement of the user's eye is in fixation or not. The method may further comprise to, on condition that the eye movement of the users eye is in fixation, applying a filter on the gaze signal, wherein the filter is adapted to decrease variance in the gaze signal.

Abstract: An augmented reality, virtual reality, or other wearable apparatus comprises an eye tracking device comprising an image sensor, a lens, and one or more processors. In some embodiments, the lens comprises a marker, and the one or more processors are configured to receive an image from the image sensor, wherein the image shows the marker, determine a distance from the image sensor to the marker based on the image, and change a calibration parameter of an eye tracking algorithm based on the distance. In some embodiments, the one or more processors are configured to receive image data from the image sensor, wherein the image data corresponds to an image as observed through the lens, determine a level or pattern of pincushion distortion in the image based on the image data, and change a calibration parameter of an eye tracking algorithm based on the level or the pattern of pincushion distortion.

Abstract: A method for applying adapted colour rendering in relation to intensity of light of wavelengths relevant to the circadian rhythm of a user, a computer program, a carrier, a system and a head-mounted device is disclosed. The method comprises receiving gaze tracking information identifying a gaze vector of the user of the system, and determining a respective location of a first area of the display and a second areas of the display based on the identified gaze vector. A first colour rendering mode is applied in the first area of the display, and a second colour rendering mode is applied in the second area of the display. The first colour rendering mode and the second colour rendering mode differ in relation to a degree of selective adaptation of intensity of light of wavelengths relevant to the circadian rhythm of the user.

Abstract: The present invention relates to a lens for eye-tracking applications. The lens comprises a first protective layer, arranged to face towards the eye to be tracked when the lens is used for eye-tracking. It also comprises at least one light source, at least partly arranged in the first protective layer, arranged to emit a first light from the first protective layer in a direction towards the eye. Moreover, it comprises at least one image capturing device, at least partly arranged in the first protective layer, arranged to receive the first light within the first protective layer. The lens further comprises an absorptive layer, arranged on the far side of the first protective layer seen from the eye to be tracked when the lens is used for eye-tracking, adapted to be absorptive for wavelengths of the majority of the first light.

Abstract: Visualizable data (Din) are obtained that represent a scene (S) with at least one object (110, 120, 130). The visualizable data (Din) describe the scene (S) as seen from a position (P). First and second measures (L1; L2) are determined, which represent extensions of one of the objects (110) in a smallest and a largest dimension respectively. An object aspect ratio (R) is calculated that represents a relationship between the first and second measures (L1; L2). Based on the object aspect ratio (R), a selection margin (M) is assigned to the object (110). The selection margin designates a zone outside of the object (110) within which zone the object (110) is validly selectable for manipulation in addition to an area (A11) of the object (110) shown towards a view (V) thereof as seen from the position (P). Thus, it is made easier to manipulatable the visualizable data (Din) in response to user input, for instance in the form of gaze-based selection commands.