Eth Zurich

Toyota Motor Europe

Toyota Jidosha Kabushiki Kaisha

Eth Zurich the Swiss Federal Institute of Technology Zurich

Vaishakh Patil

Luc Van Gool

Nicolas Vignard

Dengxin Dai

Wim Abbeloos

Alexander Liniger

Christos Sakaridis

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

Growing community of inventors

Zurich, Switzerland

Vaishakh Patil