Abstract: A computer-implemented method for reconstructing a scene in three dimensions from a plurality of images of one or more viewpoints of the scene acquired using an imaging device includes: receiving the plurality of images without receiving extrinsic or intrinsic properties of the imaging device; and processing the plurality of images using a neural network to produce a plurality of pointmaps of the scene that correspond to the plurality of images and that are aligned in a common coordinate frame, where each pointmap is a one-to-one mapping between pixels of one of the plurality of images and three-dimensional points of the scene.

Abstract: A training system includes: a transformer module having the transformer architecture and configured to perform a vision task; and a training module configured to: receive a training image having a predetermined resolution; determine N windows of tokens of pixels in the training image and mask the tokens of all of the other pixels of the training image that are outside of the N windows, where N is an integer greater than or equal to 2; input the N windows of tokens to the transformer module; train the transformer module based on an output of the transformer module generated based on the N windows of tokens; and test the transformer module using a test image having the predetermined resolution.

Abstract: A computer implemented method and system using an object-agnostic model for predicting a pose of an object in an image receives a query image having a target object therein; receives a set of reference images of the target object from different viewpoints; encodes, using a vision transformer, the received query image and the received set of reference images to generate a set of token features for the received query image and a set of token features for the received set of reference images; extracts, using a transformer decoder, information from the set of token features for the encoded reference images with respect to a set of token features for the received query image; processes, using a prediction head, the combined set of token features to generate a 2D-3D mapping and a confidence map of the query image; and processes the 2D-3D mapping and confidence map to determine the pose of the target object in the query image.

Abstract: A training system includes: a model; and a training module configured to: construct a first pair of images of at least a first portion of a first human captured at different times; construct a second pair of images of at least a second portion of a second human captured at the same time from different points of view; input the first and second pairs of images to the model; the model configured to: generate first and second reconstructed images of the at least the first portion of the first human based on the first and second pairs, respectively, and the training module is configured to selectively adjust one or more parameters of the model based on: the first reconstructed image and the second reconstructed image.

Abstract: A method includes: performing unsupervised pre-training of a model, the model including and a decoder including: obtaining a first image and a second image under different conditions or from different viewpoints; encoding, by the encoder, the first image into a representation of the first image and the second image into a representation of the second image; transforming the representation of the first image into a transformed representation; decoding, by the decoder, the transformed representation into a reconstructed image, where the transforming of the representation of the first image and the decoding of the transformed representation is based on the representation of the first image and the representation of the second image; and adjusting one or more parameters of at least one of the encoder and the decoder based on minimizing a loss; and fine-tuning the model, initialized with a set of task specific encoder parameters, for a geometric vision task.

Abstract: A computer-implemented method includes: obtaining a pair of images depicting a same scene, the pair of images including a first image with a first pixel grid and a second image with a second pixel grid, the first pixel grid different than the second pixel grid; by a neural network module having a first set of parameters: generating a first feature map based on the first image; and generating a second feature map based on the second image; determining a first correlation volume based on the first and second feature maps; iteratively determining a second correlation volume based on the first correlation volume; determining a loss for the first and second feature maps based on the second correlation volume; generating a second set of the parameters based on minimizing a loss function using the loss; and updating the neural network module to include the second set of parameters.

Abstract: A speed estimation system includes: a detection module configured to determine bounding boxes of an object moving on a surface in images, respectively, captured using a camera; a solver module configured to, based on the bounding boxes, determine a homography of the surface by solving an optimization problem, where the solver module is not trained; and a speed module configured to, using the homography, determine a speed that the object is moving on the surface.

Abstract: A computer-implemented method for training an artificial neural network with training data including samples and corresponding labels for performing a task includes: pre-training the artificial neural network to generate matrix representations that are invariant to a predetermined set of data augmentations applied to a sample, where the artificial neural network includes an encoder module and a projection module configured to generate the matrix representations based on ones of the samples, respectively; and after the pre-training, fine-tune training the artificial neural network using a loss function, wherein fine-tuning the artificial neural network includes adjusting, based on the labels, one or more weights of the projection module while maintaining constant weights of the encoder module, and where the loss function is based on a logit adjustment loss that is based on logits that are adjusted based on a class distribution of the training data.

Abstract: A speed estimation system includes: a detection module configured to determine bounding boxes of an object moving on a surface in images, respectively, captured using a camera; a solver module configured to, based on the bounding boxes, determine a homography of the surface by solving an optimization problem, where the solver module is not trained; and a speed module configured to, using the homography, determine a speed that the object is moving on the surface.

Abstract: A speed estimation system includes: a detection module configured to: detect an object on a surface in an image captured using a camera; and generate a bounding box around the object; a Jacobian module configured to generate a Jacobian for the object based on the bounding box; and a speed module configured to determine a speed that the object is traveling on the surface based on the Jacobian.

Abstract: A method of performing image retrieval includes: obtaining a query image; generating a global feature descriptor of the query image by inputting the query image into a convolutional neural network (CNN) and obtaining the global feature descriptor as an output of the CNN, where parameters of the CNN are learned during training of the CNN on a batch of training images using a listwise ranking loss function and optimizing a quantized mean average precision ranking evaluation metric; determining similarities between the query image and other images based on distances between the global feature descriptor of the query image and global feature descriptors of the other images, respectively; ranking the other images based on the similarities, respectively; and selecting a set of the other images based on the similarities between the query image and the other images.

Abstract: A speed estimation system includes: a detection module having a neural network configured to: receive a time series of images, the images including a surface having a local geometry; detect an object in the time series of images on the surface; determine pixel coordinates of the object in the time series of images, respectively; determine bounding boxes around the object in the time series of images, respectively; determine local mappings, which are not a function of global parameters describing the local geometry of the surface, between pixel coordinates and distance coordinates for the time series of images based on the bounding boxes around the object in the time series of images, respectively; and a speed module configured to determine a speed of the object traveling relative to the surface based on the distance coordinates determined for the time series of images.

Abstract: A computer-implemented method for training a neural network to perform a data processing task includes: for each data sample of a set of labeled data samples: by a first loss function for the data processing task, computing a first loss for that data sample; and by a second loss function, automatically computing a weight value for the data sample based on the first loss, the weight value indicative of a reliability of a label of the data sample predicted by the neural network for the data sample and dictating the extent to which that data sample impacts training of the neural network; and training the neural network with the set of labelled data samples according to their respective weight value.

Abstract: A system for detecting and describing keypoints in images is described. A camera is configured to capture an image including a plurality of pixels. A fully convolutional network is configured to jointly and concurrently: generate descriptors for each of the pixels, respectively; generate reliability scores for each of the pixels, respectively; and generate repeatability scores for each of the pixels, respectively. A scoring module is configured to generate scores for the pixels, respectively, based on the reliability scores and the repeatability scores of the pixels, respectively. A keypoint list module is configured to: select X of the pixels having the X highest scores, where X is an integer greater than 1; and generate a keypoint list including: locations of the selected X pixels; and the descriptors of the selected X pixels.

Abstract: A method for detecting a point of interest (POI) change in a pair of inputted POI images. A first processor of the method: generates triplets of training POI images using a base of training POI images and trains a convolutional neural network (CNN) of three-stream Siamese type based on the triplets of training POI images. A second processor of the method: computes, for each image of the pair of inputted POI images, a descriptor of that image using a stream of the CNN of three-stream Siamese type, computes a similarity score based on the descriptors of the images of the pair of inputted POI images using a similarity score function, and selectively detects the POI change based on the similarity score. A third processor of the method generates the base of training POI images to include an initial set of POI images and a set of synthetic POI images.

Abstract: A system for detecting and describing keypoints in images is described. A camera is configured to capture an image including a plurality of pixels. A fully convolutional network is configured to jointly and concurrently: generate descriptors for each of the pixels, respectively; generate reliability scores for each of the pixels, respectively; and generate repeatability scores for each of the pixels, respectively. A scoring module is configured to generate scores for the pixels, respectively, based on the reliability scores and the repeatability scores of the pixels, respectively. A keypoint list module is configured to: select X of the pixels having the X highest scores, where X is an integer greater than 1; and generate a keypoint list including: locations of the selected X pixels; and the descriptors of the selected X pixels.

Abstract: A method for training a convolutional neural network for classification of actions performed by subjects in a video is realized by (a) for each frame of the video, for each key point of the subject, generating a heat map of the key point representing a position estimation of the key point within the frame; (b) colorizing each heat map as a function of the relative time of the corresponding frame in the video; (c) for each key point, aggregating all the colorized heat maps of the key point into at least one image representing the evolution of the position estimation of the key point during the video; and training the convolutional neural network using as input the sets associated to each training video of images representing the evolution of the position estimation of each key point during the video.

Abstract: A method of performing image retrieval includes: obtaining a query image; generating a global feature descriptor of the query image by inputting the query image into a convolutional neural network (CNN) and obtaining the global feature descriptor as an output of the CNN, where parameters of the CNN are learned during training of the CNN on a batch of training images using a listwise ranking loss function and optimizing a quantized mean average precision ranking evaluation metric; determining similarities between the query image and other images based on distances between the global feature descriptor of the query image and global feature descriptors of the other images, respectively; ranking the other images based on the similarities, respectively; and selecting a set of the other images based on the similarities between the query image and the other images.

Abstract: A method for detecting a point of interest (POI) change in a pair of inputted POI images. A first processor of the method: generates triplets of training POI images using a base of training POI images and trains a convolutional neural network (CNN) of three-stream Siamese type based on the triplets of training POI images. A second processor of the method: computes, for each image of the pair of inputted POI images, a descriptor of that image using a stream of the CNN of three-stream Siamese type, computes a similarity score based on the descriptors of the images of the pair of inputted POI images using a similarity score function, and selectively detects the POI change based on the similarity score. A third processor of the method generates the base of training POI images to include an initial set of POI images and a set of synthetic POI images.

Abstract: A method for training a convolutional neural network for classification of actions performed by subjects in a video is realized by (a) for each frame of the video, for each key point of the subject, generating a heat map of the key point representing a position estimation of the key point within the frame; (b) colorizing each heat map as a function of the relative time of the corresponding frame in the video; (c) for each key point, aggregating all the colorized heat maps of the key point into at least one image representing the evolution of the position estimation of the key point during the video; and training the convolutional neural network using as input the sets associated to each training video of images representing the evolution of the position estimation of each key point during the video.