Eth Zurich

Toyota Jidosha Kabushiki Kaisha

Katholieke Universiteit Leuven

Toyota Motor Europe

Pxl Vision Ag

Katholieke Universiteit Leuven, K.u. Leuven Research & Development

Eth Zurich the Swiss Federal Institute of Technology Zurich

Luc Van Gool

Dengxin Dai

Stamatios Georgoulis

Gabriel Othmezouri

Wim Abbeloos

Benjamin Fankhauser

Christos Sakaridis

Michael Goettlicher

Marcus Hudritsch

Mikhail Vorobiev

Suman Saha

Nevena Shamoska

Magdalena Polac

Nicolas Vignard

Marc Proesmans

Hiroaki Shimizu

Arun Balajee Vasudevan

Vaishakh Patil

Liqian Ma

Simon Vandenhende

Wouter Van Gansbeke

Anton Obukhov

Maksim Rakhuba

Menelaos Kanakis

Martin Hahner

Yu Fisher

Ozan Unal

Niclas VÖDISCH

Ke Li

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.

Method for training a neural network to describe an environment on the basis of an audio signal, and the corresponding neural network

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.

System and method for training a model to perform semantic segmentation on low visibility images using high visibility images having a close camera view

A computer-implemented method for training a classifier (Φη), including: training a pretext model (ΦΘ) to learn a pretext task, so as to minimize a distance between an output of a source sample via the pretext model (ΦΘ) and an output of a corresponding transformed sample via the pretext model (ΦΘ), the transformed sample being a sample obtained by applying a transformation (T) to the source sample; S) determining a neighborhood (NXi) of samples (Xi) of a dataset (SD) in the embedding space; S) training the classifier (Φη) to predict respective estimated probabilities Φηj(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.

Computer-implemented training method, classification method and system and computer-readable recording medium

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.

System for image completion

A depth maps prediction system comprising a neural network () configured to receive images (I) of a scene at successive time steps (t−1, t, t+1, . . . ) and comprising three sub-networks: an encoder (), a ConvLSTM () and a decoder (). The neural network () is configured so that at each time step: a) the encoder sub-network () processes an image (I) and outputs a low resolution initial image representation (X); b) the CONVLSTM sub-network () processes the initial image representation (X), values for a previous time step (t−1) of an internal state (C(t−1)) and of an LSTM hidden variable data (H(t−1)) of the ConvLSTM sub-network, and outputs updated values of the internal state (C(t)) and of the LSTM hidden variable data (H(t)); andc) the decoder sub-network () inputs the LSTM output data (LOD) and generates a predicted dense depth map (D″) for the inputted image (I).

Depth maps prediction system and training method for such a system

A system and a method for training a model to be used for semantic segmentation of images, comprising:

Method and a system training a model to perform semantic segmentation on foggy images

A system for remote identification of users. The system uses deep learning techniques for authenticating a user from an identification document and using automated verification of identification documents. Identification documents may be authenticated by validating security features. The system may determine features expected in a valid identification document and determine whether those features are present, employing techniques, such as determining whether direction-sensitive features are present. Liveness of a user indicated by the identification document may be determined with a deep learning model trained for identification of facial spoofing attacks.

ID verification with a mobile device

A system for remote identification of users. The system uses deep learning techniques for authenticating a user from an identification document, using automated verification of identification documents and detection that a live person identified by the document is present. Liveness of a user indicated by the identification document may be determined with a deep learning model trained for identification of facial spoofing attacks. The deep learning model may be trained using training data extracted from facial feature locations of training images.

Facial liveness detection with a mobile device

Growing community of inventors

Zurich, Switzerland

Luc Van Gool