Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve performance of an artificial intelligence based (AI-based) model on datasets having different distributions. An example apparatus includes interface circuitry to access data, computer readable instructions, and processor circuitry to at least one of instantiate or execute the computer readable instructions to implement adversarial evaluation circuitry, convolution circuitry, and output control circuitry. The example adversarial evaluation circuitry is to determine whether the data is to be processed as adversarial data. The example convolution circuitry is to, based on whether the data is to be processed as the adversarial data, determine a convolution of an input tensor and (1) a parameter tensor corresponding to a layer of the AI-based model or (2) a noisy parameter tensor generated based on the parameter tensor. The example output control circuitry is to output a classification of the data based on the convolution.

Abstract: The present disclosure is related to techniques for optimizing artificial intelligence (AI) and/or machine learning (ML) models to reduce resource consumption while maintaining or improving AI/ML model performance. A sparse distillation framework (SDF) is provided for producing a class of parameter and compute efficient AI/ML models suitable for resource constrained applications. The SDF simultaneously distills knowledge from a compute heavy teacher model while also pruning a student model in a single pass of training, thereby reducing training and tuning times considerably. A self-attention mechanism may also replace CNNs or convolutional layers of a CNN to have better translational equivariance. Other embodiments may be described and/or claimed.

Abstract: Techniques and systems are provided for tracking objects in one or more images. For example, a trained network can be applied to a first image of a sequence of images to detect one or more objects in the first image. The trained network can be applied to less than all images of the sequence of images. A second image of the sequence of images and a detection result from application of the trained network to the first image are obtained. The detection result includes the detected one or more objects from the first image. A first object tracker can be applied to the second image using the detection result from application of the trained network to the first image. Applying the first object tracker can include adjusting one or more locations of one or more bounding boxes associated with the detected one or more objects in the second image to track the detected one or more objects in the second image.

Abstract: Techniques and systems are provided for processing one or more images. In one example, a method of processing a plurality of images comprises: obtaining a first image captured using a first aperture setting; obtaining a second image captured using a second aperture setting, the first aperture setting being associated with a smaller aperture size than an aperture size associated with the second aperture setting; detecting pixels of the first image having lens flare; and generating an output image by combining the first image and the second image, the first image and the second image being combined by replacing the pixels of the first image having the lens flare with corresponding pixels of the second image.

Abstract: A method for determining a pixel value of a texture pixel associated with a three-dimensional scan of an object includes prioritizing a sequence of image frames in a queue based on one or more prioritization parameters. The method also includes selecting a first image frame from the queue. The method also includes determining a pixel value of the particular texture pixel in the first image frame. The method further includes selecting a second image frame from the queue. The second image frame has a higher priority than the first image frame based on the one or more prioritization parameters. The method also includes modifying the pixel value of the particular texture pixel based on a pixel value of the particular texture pixel in the second image frame to generate a modified pixel value of the particular texture pixel.

Abstract: Methods and apparatuses are disclosed for assisting a user in performing a three dimensional scan of an object. An example user device to assist with scanning may include a processor. The user device may further include a scanner coupled to the processor and configured to perform a three dimensional scan of an object. The user device may also include a display to display a graphical user interface, wherein the display is coupled to the processor. The user device may further include a memory coupled to the processor and the display, the memory including one or more instructions that when executed by the processor cause the graphical user interface to display a target marker for a three dimensional (3D) scan and display a scanner position marker to assist in moving the scanner to a preferred location and direction.

Abstract: A method for texture reconstruction associated with a three-dimensional scan of an object includes scanning, at a processor, a sequence of image frames captured by an image capture device at different three-dimensional viewpoints. The method also includes generating a composite confidence map based on the sequence of image frames. The composite confidence map includes pixel values for scanned pixels in the sequence of image frames. The method further includes identifying one or more holes of a three-dimensional model based on the composite confidence map.

Abstract: Techniques and systems are provided for tracking objects in one or more images. For example, a trained network can be applied to a first image of a sequence of images to detect one or more objects in the first image. The trained network can be applied to less than all images of the sequence of images. A second image of the sequence of images and a detection result from application of the trained network to the first image are obtained. The detection result includes the detected one or more objects from the first image. A first object tracker can be applied to the second image using the detection result from application of the trained network to the first image. Applying the first object tracker can include adjusting one or more locations of one or more bounding boxes associated with the detected one or more objects in the second image to track the detected one or more objects in the second image.

Abstract: A neural network processing system be configured to: (a) execute a first neural network and a second neural network; (b) run a first data segment through the first neural network to return a first score and run a second data segment through the second neural network to return a second score; (c) compare the first score with the second score; and (d) retrain the first neural network based on the comparison

Abstract: A method for generating one or more two-dimensional texture maps of an object includes receiving an image frame that includes at least a portion of the object from an image capture device. The method also includes determining, at a processor, a color of a particular portion of the object using the image frame and determining a material of the particular portion of the object using the image frame. The method further includes determining at least one other property of the particular portion of the object based on the material. The method also includes generating a pixel value representative of the color of the particular portion of the object and representative of the at least one other property of the particular portion of the object. The method also includes generating at least one two-dimensional texture map based on the pixel value.

Abstract: Methods and apparatuses are disclosed for assisting a user in performing a three dimensional scan of an object. An example user device to assist with scanning may include a processor. The user device may further include a scanner coupled to the processor and configured to perform a three dimensional scan of an object. The user device may also include a display to display a graphical user interface, wherein the display is coupled to the processor. The user device may further include a memory coupled to the processor and the display, the memory including one or more instructions that when executed by the processor cause the graphical user interface to display a target marker for a three dimensional (3D) scan and display a scanner position marker to assist in moving the scanner to a preferred location and direction.

Abstract: A method for adjusting pixel colors between image frames includes scanning, at a processor, a first image frame of a sequence of image frames. The method also includes determining a grayscale threshold based on characteristics of the first image frame to identify gray pixel candidates in the first image frame. The method further includes adjusting a pixel value of each pixel in the first image frame based on a chromatic adaptation transform estimation. The chromatic adaptation transform estimation is based on the gray pixel candidates. The grayscale threshold may be computed for each image frame in the sequence of image frames.

Abstract: A method for determining a region of an image is described. The method includes presenting an image of a scene including one or more objects. The method also includes receiving an input selecting a single point on the image corresponding to a target object. The method further includes obtaining a motion mask based on the image. The motion mask indicates a local motion section and a global motion section of the image. The method further includes determining a region in the image based on the selected point and the motion mask.

Abstract: A method for generating one or more two-dimensional texture maps of an object includes receiving an image frame that includes at least a portion of the object from an image capture device. The method also includes determining, at a processor, a color of a particular portion of the object using the image frame and determining a material of the particular portion of the object using the image frame. The method further includes determining at least one other property of the particular portion of the object based on the material. The method also includes generating a pixel value representative of the color of the particular portion of the object and representative of the at least one other property of the particular portion of the object. The method also includes generating at least one two-dimensional texture map based on the pixel value.

Abstract: A method performed by an electronic device is described. The method includes determining a local motion pattern by determining a set of local motion vectors within a region of interest between a previous frame and a current frame. The method also includes determining a global motion pattern by determining a set of global motion vectors between the previous frame and the current frame. The method further includes calculating a separation metric based on the local motion pattern and the global motion pattern. The separation metric indicates a motion difference between the local motion pattern and the global motion pattern. The method additionally includes tracking an object based on the separation metric.

Abstract: A method for determining a region of an image is described. The method includes presenting an image of a scene including one or more objects. The method also includes receiving an input selecting a single point on the image corresponding to a target object. The method further includes obtaining a motion mask based on the image. The motion mask indicates a local motion section and a global motion section of the image. The method further includes determining a region in the image based on the selected point and the motion mask.

Abstract: A particular method includes determining, based on data received from at least one motion sensor, a movement of a mobile device from a first position to a second position. The method also includes computing a three-dimensional (3D) model of an object based on a first image of the object corresponding to a first view of the object from the first position of the mobile device, a second image of the object corresponding to a second view of the object from the second position of the mobile device, and the movement of the mobile device.

Abstract: A method includes receiving, from an image capture device, a first image frame of a sequence of image frames. The method also includes estimating, at a processor, a camera pose corresponding to the first image frame by comparing the first image frame to a second image frame. The second image frame precedes the first image frame in the sequence of image frames. The method further includes estimating, at the processor, a refined camera pose corresponding to the first image frame by comparing the first image frame to a keyframe. The keyframe corresponds to a particular image frame that precedes the second image frame in the sequence of image frames.

Abstract: A method includes generating, at an electronic device, a three-dimensional model of an object based on a sequence of images captured by an image capture device associated with the electronic device. The method further includes displaying the three-dimensional model via a display device associated with the electronic device. The method also includes, based on detecting that the three-dimensional model includes an anomaly, presenting, via the display device, one or more selectable options to enable correction of the anomaly.

Abstract: A method for texture reconstruction associated with a three-dimensional scan of an object includes scanning, at a processor, a sequence of image frames captured by an image capture device at different three-dimensional viewpoints. The method also includes generating a composite confidence map based on the sequence of image frames. The composite confidence map includes pixel values for scanned pixels in the sequence of image frames. The method further includes identifying one or more holes of a three-dimensional model based on the composite confidence map.