Example embodiments allow for training of encoders (e.g., artificial neural networks (ANNs)) to generate a color palette based on an input image. The color palette can then be used to generate, using the input image, a quantized, reduced color depth image that corresponds to the input image. Differences between a plurality of such input images and corresponding quantized images are used to train the encoder. Encoders trained in this manner are especially suited for generating color palettes used to convert images into different reduced color depth image file formats. Such an encoder also has benefits, with respect to memory use and computational time or cost, relative to the median-cut algorithm or other methods for producing reduced color depth color palettes for images.

Example embodiments allow for training of encoders (e.g., artificial neural networks (ANNs)) to generate a color palette based on an input image. The color palette can then be used to generate, using the input image, a quantized, reduced color depth image that corresponds to the input image. Differences between a plurality of such input images and corresponding quantized images are used to train the encoder. Encoders trained in this manner are especially suited for generating color palettes used to convert images into different reduced color depth image file formats. Such an encoder also has benefits, with respect to memory use and computational time or cost, relative to the median-cut algorithm or other methods for producing reduced color depth color palettes for images.

An apparatus comprising an interface, a structured light projector and a processor. The interface may receive pixel data. The structured light projector may generate a structured light pattern. The processor may process the pixel data arranged as video frames, perform operations using a convolutional neural network to determine a binarization result and an offset value and generate disparity and depth maps in response to the video frames, the structured light pattern, the binarization result, the offset value and a removal of error points. The convolutional neural network may perform a partial block summation to generate a convolution result, compare the convolution result to a speckle value to determine the offset value, generate an adaptive result in response to performing a convolution operation, compare the video frames to the adaptive result to generate the binarization result for the video frames, and remove the error points from the binarization result.

Systems and methods are directed to automatically creating customized whiteboard backgrounds. A network system accesses metadata associated with a virtual presentation (e.g., title, topic, tenant identifier). First image data is identified based on first data of the metadata and second image data is identified based on second data of the metadata. Using the first image data and the second image data, the network system generates a plurality of whiteboard backgrounds by combining a first object obtained from the first image data with a second object obtained from the second image data to form each whiteboard background. The network system then causes presentation of a representation of each of the plurality of whiteboard backgrounds on a user interface of a host, who can select one of the representations. In response to receiving a selection, a whiteboard background corresponding to the selected representation is displayed as background on a whiteboard canvas.

Systems and methods are directed to automatically creating customized whiteboard backgrounds. A network system accesses metadata associated with a virtual presentation (e.g., title, topic, tenant identifier). First image data is identified based on first data of the metadata and second image data is identified based on second data of the metadata. Using the first image data and the second image data, the network system generates a plurality of whiteboard backgrounds by combining a first object obtained from the first image data with a second object obtained from the second image data to form each whiteboard background. The network system then causes presentation of a representation of each of the plurality of whiteboard backgrounds on a user interface of a host, who can select one of the representations. In response to receiving a selection, a whiteboard background corresponding to the selected representation is displayed as background on a whiteboard canvas.

The invention relates to a device and a method for performing an eye gaze mapping (M), in which at least one point of vision (B) and/or a viewing direction of at least one person (10) in relation to at least one scene recording (S) of a scene (12) viewed by the at least one person (10) is mapped onto a reference (R). At least a part of an algorithm (A1, A2, A3) for performing the eye gaze mapping (M) is thereby selected from multiple predetermined algorithms (A1, A2, A3) as a function of at least one parameter (P), and the eye gaze mapping (M) is performed on the basis of the at least one part of the algorithm (A1, A2, A3).

A method for dynamically quantizing feature maps of a received image. The method includes convolving an image based on a predicted maximum value, a predicted minimum value, trained kernel weights and the image data. The input data is quantized based on the predicted minimum value and predicted maximum value. The output of the convolution is computed into an accumulator and re-quantized. The re-quantized value is output to an external memory. The predicted min value and the predicted max value are computed based on the previous max values and min values with a weighted average or a pre-determined formula. Initial min value and max value are computed based on known quantization methods and utilized for initializing the predicted min value and predicted max value in the quantization process.

A method for dynamically quantizing feature maps of a received image. The method includes convolving an image based on a predicted maximum value, a predicted minimum value, trained kernel weights and the image data. The input data is quantized based on the predicted minimum value and predicted maximum value. The output of the convolution is computed into an accumulator and re-quantized. The re-quantized value is output to an external memory. The predicted min value and the predicted max value are computed based on the previous max values and min values with a weighted average or a pre-determined formula. Initial min value and max value are computed based on known quantization methods and utilized for initializing the predicted min value and predicted max value in the quantization process.

An image reading apparatus includes a conveyance unit configured to convey an original; a reading unit comprising a reading sensor, the reading sensor having a light receiving element to receive light of a first color and a light receiving element to receive light of a second color that is different from the first color, wherein the reading unit is configured to read an image of the original conveyed by the conveyance unit by using the reading sensor to generate image data which represents a reading result of the reading unit; at least one processor configured to: determine a first abnormal position that is a position in a first direction of an abnormal pixel of the first color in an image represented by the image data.

Systems and methods for encoding regions containing an element of interest in a sequence of images with a high resolution are provided. Such systems and methods can include a camera that can capture the sequence of images of a monitored region, a detection processor that can identify a first region that contains an element of interest within the sequence of images, and an encoder that can encode the first region within a first subset of the sequence of images with a first resolution and encode a second region within the first subset of the sequence of images outside of the first region with a second resolution that is less than the first resolution, wherein a number of the sequence of images in the first subset of the sequence of images is less than all of the sequence of images and is based on a predefined parameter.