Abstract: A neural network, a system using this neural network and a method for training a neural network to output a description of the environment in the vicinity of at least one sound acquisition device on the basis of an audio signal acquired by the sound acquisition device, the method including: obtaining audio and image training signals of a scene showing an environment with objects generating sounds, obtaining a target description of the environment seen on the image training signal, inputting the audio training signal to the neural network so that the neural network outputs a training description of the environment, and comparing the target description of the environment with the training description of the environment.

Abstract: A system and a method for training a semantic segmentation model includes obtaining a plurality of sets of images each having an index z for visibility, iteratively training the model. Iteratively training the model includes (a) for each z above 1, obtaining preliminary semantic segmentation labels for each image of the set of images of index z?1 by applying the model to each image of the set of images of index z?1, (b) processing each preliminary semantic segmentation labels using semantic segmentation labels obtained using the model on a selected image of index 1, and obtaining processed semantic segmentation labels, (c) training the model using the set of images of index z?1 and the associated processed semantic segmentation labels, and (d) performing steps (a) to (c) for z+1.

Abstract: A system for generating a mask for object instances in an image is provided. The system includes a first module comprising a trained neural network and configured to input the image to the neural network, wherein the neural network is configured to generate: pixel offset vectors for the pixels of the object instance configured to point towards a unique center of an object instance, the pixel offset vectors thereby forming a cluster with a cluster distribution, and for each object instance an estimate of said cluster distribution defining a margin for determining which pixels belong to the object instance. A method for training a neural network map to be used for generating a mask for object instances in an image is also provided.

Abstract: A computer-implemented method for training a classifier (??), including: training a pretext model (??) to learn a pretext task, so as to minimize a distance between an output of a source sample via the pretext model (??) and an output of a corresponding transformed sample via the pretext model (??), the transformed sample being a sample obtained by applying a transformation (T) to the source sample; S20) determining a neighborhood (NXi) of samples (Xi) of a dataset (SD) in the embedding space; S30) training the classifier (??) to predict respective estimated probabilities ??j(Xi), j=1 . . . C, for a sample (Xi) to belong to respective clusters (Cj), by using a second training criterion which tends to: maximize a likelihood for a sample and its neighbors (Xj) of its neighborhood (Nxi) to belong to the same cluster; and force the samples to be distributed over several clusters.

Abstract: A system for image completion is disclosed. The system comprises a coordinate generation module configured to receive past frames and a present frame having a first field-of-view and to generate a set of coordinate maps, one for each of the received past frames; and a frame aggregation module configured to receive as input the past frames, the present frame, and the coordinate maps and to synthesize, based on said input, a present frame having a second field-of-view.

Abstract: The disclosure relates to system for processing an image of at least one camera. The camera has predetermined camera parameters including a lens distortion and a camera pose with respect to a predefined reference frame. The system comprises: a trained neural network with a predefined architecture, the neural network being configured to receive the image of the camera as input and to predict in response at least one characteristic, wherein the neural network architecture comprises at least one static feature map configured to encode the predetermined camera parameters including the lens distortion and/or the camera pose.

Abstract: A computer-implemented method for training a classifier (??), including: training a pretext model (??) to learn a pretext task, so as to minimize a distance between an output of a source sample via the pretext model (??) and an output of a corresponding transformed sample via the pretext model (??), the transformed sample being a sample obtained by applying a transformation (T) to the source sample; S20) determining a neighborhood (NXi) of samples (Xi) of a dataset (SD) in the embedding space; S30) training the classifier (??) to predict respective estimated probabilities ??j(Xi), j=1 . . . C, for a sample (Xi) to belong to respective clusters (Cj), by using a second training criterion which tends to: maximize a likelihood for a sample and its neighbors (Xj) of its neighborhood (Nxi) to belong to the same cluster; and force the samples to be distributed over several clusters.

Abstract: A method and system detects and localizes multiple instances of an object by first acquiring a frame of a three-dimensional (3D) scene with a sensor, and extracting features from the frame. The features are matched according to appearance similarity and triplets are formed among matching features. Based on 3D locations of the corresponding points in the matching triplets, a geometric transformation is computed. Matching triplets are clustered according to the computed geometric transformations. Since the set of features coining from two different object instances should have a single geometric transform, the output of clustering provides the features and poses of each object instance in the image.

Abstract: A method and system detects and localizes multiple instances of an object by first acquiring a frame of a three-dimensional (3D) scene with a sensor, and extracting features from the frame. The features are matched according to appearance similarity and triplets are formed among matching features. Based on 3D locations of the corresponding points in the matching triplets, a geometric transformation is computed. Matching triplets are clustered according to the computed geometric transformations. Since the set of features coining from two different object instances should have a single geometric transform, the output of clustering provides the features and poses of each object instance in the image.