Abstract: Methods and systems for estimation of a 3D hand pose are disclosed. A 2D image containing a detected hand is processed using a U-net network to obtain a global feature vector and a heatmap for the keypoints of the hand. Information from the global feature vector and the heatmap are concatenated to obtain a set of input tokens that are processed using a transformer encoder to obtain a first set of 2D keypoints representing estimated 2D locations of the keypoints in a first view. The first set of 2D keypoints are inputted as a query to a transformer decoder, to obtain a second set of 2D keypoints representing estimated 2D locations of the keypoints in a second view. The first and second sets of 2D keypoints are aggregated to output the set of estimated 3D keypoints.

Abstract: A processing entity generates a model for estimating scene illumination colour for a source image captured by a camera The processing entity acquires a set of images, captured by a respective camera, the set of images as a whole including images captured by multiple cameras; forms a set of tasks by assigning each image of the images set to a respective task such that images in the same task have in common that a the images are in a predetermined range; trains model parameters by repeatedly: selecting at least one of the tasks, forming an interim set of model parameters based on a first subset of the images of that task, estimating the quality of the interim set of model parameters against a second subset of the images of that task and updating the parameters of the model based on the interim set of parameters and the estimated quality.

Abstract: Methods and systems for estimation of a 3D hand pose are disclosed. A 2D image containing a detected hand is processed using a U-net network to obtain a global feature vector and a heatmap for the keypoints of the hand. Information from the global feature vector and the heatmap are concatenated to obtain a set of input tokens that are processed using a transformer encoder to obtain a first set of 2D keypoints representing estimated 2D locations of the keypoints in a first view. The first set of 2D keypoints are inputted as a query to a transformer decoder, to obtain a second set of 2D keypoints representing estimated 2D locations of the keypoints in a second view. The first and second sets of 2D keypoints are aggregated to output the set of estimated 3D keypoints.

Abstract: A device for estimating a scene illumination color for a source image is configured to: determine a set of candidate illuminants and for each of the candidate illuminants, determine a respective correction of the source image; for each of the candidate illuminants, apply the respective correction to the source image to form a corresponding set of corrected images; for each corrected image from the set of corrected images, implement a trained data-driven model to estimate a respective probability of achromaticity of the respective corrected image; and based on the estimated probabilities of achromaticity for the set of corrected images, obtain a final estimate of the scene illumination color for the source image. This approach allows for the evaluation of multiple candidate illuminates to determine an estimate of the scene illumination color.

Abstract: An image processing device comprising a processor configured to generate a refocused image from an input image and an map indicating depth information for the image, by the steps of: for each of a plurality of planes associated with respective depths within the image: generating a depth mask having values indicating whether regions of the input image are within a specified range of the plane, wherein an assessment of whether a region is within the specified range of the plane is made through the evaluation of a differentiable function of the range between regions of the input image and the plane as determined from the map; generating a masked image from the input image and the generated depth mask; refocusing the masked image using a blurring kernel to generate a refocused partial image; and generating the refocussed image from the plurality of refocussed partial images.

Abstract: An image processing apparatus for estimating a depth field over a field of view. The apparatus comprises one or more processors configured to receive a captured polarisation image representing a polarisation of light received at a first set of multiple locations over the field of view; process the captured polarisation image using a first trained neural network to form a first estimate of depths to one or more locations over the field of view; receive ranging data representing environmental distances from a datum to one or more locations over the field of view; and process the ranging data using a second trained neural network to form a second estimate of depths to a second set of multiple locations over the field of view.

Abstract: A device for categorising regions in images is disclosed. The device comprising: an input for receiving a first set of images, and defining one or more regions of for each image of the first set of images and a categorisation for the one or more regions, and a second set of images, and a categorisation for each image of the second set; and a processor configured to train a first machine learning algorithm to categorise features in images by: processing the images of the first and second set using the first algorithm to estimate feature regions in the images and a categorisation for each of the feature regions, and training the first algorithm in dependence on the categorisations received for the images of the first and second sets.

Abstract: A computer system and method are provided for training a machine learning system to perform a classification task by classifying input data into one of a plurality of classes. The system is configured to: receive per class training data from which per class representations can be derived, wherein each class is described by multiple representations; process the training data to form, for at least one class, a first proxy for a relatively global portion of an item of training data and multiple proxies for distinct relatively local portions of the item of training data, each proxy corresponding to a representation of the data belonging to that class.

Abstract: An image processing apparatus and a method are provided. The apparatus comprises a plurality of processing modules configured to operate in series to refine a raw image captured by a camera, the modules comprising a first module and a second module, each of which independently implements a respective trained artificial intelligence model, wherein: the first module implements an image transformation operation that performs an operation from the set comprising: (i) an essentially pixel-level operation that increases sharpness of an image input to the module, (ii) an essentially pixel-level operation that decreases sharpness of an image input to the module, (iii) an essentially pixel-block-level operation on an image input to the module; and the second module as a whole implements a different operation from the said set.

Abstract: A device for estimating a scene illumination color for a source image is configured to: determine a set of candidate illuminants and for each of the candidate illuminants, determine a respective correction of the source image; for each of the candidate illuminants, apply the respective correction to the source image to form a corresponding set of corrected images; for each corrected image from the set of corrected images, implement a trained data-driven model to estimate a respective probability of achromaticity of the respective corrected image; and based on the estimated probabilities of achromaticity for the set of corrected images, obtain a final estimate of the scene illumination color for the source image. This approach allows for the evaluation of multiple candidate illuminates to determine an estimate of the scene illumination color.

Abstract: An image processing device comprising a processor configured to generate a refocused image from an input image and an map indicating depth information for the image, by the steps of: for each of a plurality of planes associated with respective depths within the image: generating a depth mask having values indicating whether regions of the input image are within a specified range of the plane, wherein an assessment of whether a region is within the specified range of the plane is made through the evaluation of a differentiable function of the range between regions of the input image and the plane as determined from the map; generating a masked image from the input image and the generated depth mask; refocusing the masked image using a blurring kernel to generate a refocused partial image; and generating the refocussed image from the plurality of refocussed partial images.

Abstract: An image processing apparatus and a method are provided. The apparatus comprises a plurality of processing modules configured to operate in series to refine a raw image captured by a camera, the modules comprising a first module and a second module, each of which independently implements a respective trained artificial intelligence model, wherein: the first module implements an image transformation operation that performs an operation from the set comprising: (i) an essentially pixel-level operation that increases sharpness of an image input to the module, (ii) an essentially pixel-level operation that decreases sharpness of an image input to the module, (iii) an essentially pixel-block-level operation on an image input to the module; and the second module as a whole implements a different operation from the said set.

Abstract: A processing entity generates a model for estimating scene illumination colour for a source image captured by a camera The processing entity acquires a set of images, captured by a respective camera, the set of images as a whole including images captured by multiple cameras; forms a set of tasks by assigning each image of the images set to a respective task such that images in the same task have in common that a the images are in a predetermined range; trains model parameters by repeatedly: selecting at least one of the tasks, forming an interim set of model parameters based on a first subset of the images of that task, estimating the quality of the interim set of model parameters against a second subset of the images of that task and updating the parameters of the model based on the interim set of parameters and the estimated quality.