Abstract: A variational auto-encoder model is trained to generate probabilities of action categories and probabilities of inter-arrival times of next action from a sequence of past actions by generating a concatenated representation of each action and associated time, encoding the concatenated representations, determining a conditional prior distribution for a next action, determining a conditional posterior distribution for the current action, sampling a latent variable from the conditional prior distribution, generating a probability distribution over a current action category, and generating a probability distribution over inter-arrival times for the current action category.

Abstract: A system and method for white balancing a digital image. The method including downsampling the digital image to generate a downsampled image; processing the downsampled image with a plurality of preset white balance settings to generate a plurality of white balanced downsampled images; processing the input image at a fixed white balanced setting to produce an initial image; inputting the white balanced downsampled images to a deep neural network to generate a weighting map, the weighting map including weights of the preset white balance settings at windows of the downsampled images; generating a white balanced output image by applying the weighting map to the initial image; and outputting the white balanced output image.

Abstract: Provided is a method of training a neural radiance field and producing a rendering of a 3D scene from a novel viewpoint with view-dependent effects. The neural radiance field is initially trained using a first loss associated with a plurality of unmasked regions associated with a reference image and a plurality of target images. The training may also be updated using a second loss associated with a depth estimate of a masked region in the reference image. The training may also be further updated using a third loss associated with a view-substituted image associated with a respective target image. The view-substituted image is a volume rendering from the reference viewpoint across pixels with view-substituted target colors. In some embodiments, the neural radiance field is additionally trained with a fourth loss. The fourth loss is associated with dis-occluded pixels in a target image.

Abstract: A system and method for white balancing a digital image. The method including downsampling the digital image to generate a downsampled image; processing the downsampled image with a plurality of preset white balance settings to generate a plurality of white balanced downsampled images; processing the input image at a fixed white balanced setting to produce an initial image; inputting the white balanced downsampled images to a deep neural network to generate a weighting map, the weighting map including weights of the preset white balance settings at windows of the downsampled images; generating a white balanced output image by applying the weighting map to the initial image; and outputting the white balanced output image.

Abstract: A variational hyper recurrent neural network (VHRNN) can be trained by, for each step in sequential training data: determining a prior probability distribution for a latent variable from a prior network of the VHRNN using an initial hidden state; determining a hidden state from a recurrent neural network (RNN) of the VHRNN using an observation state, the latent variable and the initial hidden state; determining an approximate posterior probability distribution for the latent variable from an encoder network of the VHRNN using the observation state and the initial hidden state; determining a generating probability distribution for the observation state from a decoder network of the VHRNN using the latent variable and the initial hidden state; and maximizing a variational lower bound of a marginal log-likelihood of the training data. The trained VHRNN can be used to generate sequential data.

Abstract: A variational hyper recurrent neural network (VHRNN) can be trained by, for each step in sequential training data: determining a prior probability distribution for a latent variable from a prior network of the VHRNN using an initial hidden state; determining a hidden state from a recurrent neural network (RNN) of the VHRNN using an observation state, the latent variable and the initial hidden state; determining an approximate posterior probability distribution for the latent variable from an encoder network of the VHRNN using the observation state and the initial hidden state; determining a generating probability distribution for the observation state from a decoder network of the VHRNN using the latent variable and the initial hidden state; and maximizing a variational lower bound of a marginal log-likelihood of the training data. The trained VHRNN can be used to generate sequential data.

Abstract: A variational auto-encoder model is trained to generate probabilities of action categories and probabilities of inter-arrival times of next action from a sequence of past actions by generating a concatenated representation of each action and associated time, encoding the concatenated representations, determining a conditional prior distribution for a next action, determining a conditional posterior distribution for the current action, sampling a latent variable from the conditional prior distribution, generating a probability distribution over a current action category, and generating a probability distribution over inter-arrival times for the current action category.

Abstract: The inventive systems and methods relate to the field of matching toolmarks for firearm forensics having a retrographic sensor to provide a three dimensional representation of a surface of an object for heatmapping analyzed matching geometric features.

Abstract: The inventive systems and methods relate to the field of matching toolmarks for firearm forensics having a retrographic sensor to provide a three dimensional representation of a surface of an object for heatmapping analyzed matching geometric features.