Multi-scale recurrent decoder for monocular depth estimation
AssigneeToyota Research Institute, Inc.
InventorsVitor Guizilini, Adrien David Gaidon
Life of this patent
Estimating the term…
Loading patent…
AssigneeToyota Research Institute, Inc.
InventorsVitor Guizilini, Adrien David Gaidon
Estimating the term…
A method for estimating depth is presented. The method includes generating, at each decoding layer of a neural network, decoded features of an input image. The method also includes upsampling, at each decoding layer, the decoded features to a resolution of a final output of the neural network. The method still further includes concatenating, at each decoding layer, the upsampled decoded features with features generated at a convolution layer of the neural network. The method additionally includes sequentially receiving the concatenated upsampled decoded features at a long-short term memory (LSTM) module of the neural network from each decoding layer. The method still further includes generating, at the LSTM module, a depth estimate of the input image after receiving the concatenated upsampled inverse depth estimate from a final layer of a decoder of the neural network. The method also includes controlling an action of an agent based on the depth estimate.
A method for estimating depth, comprising:
An apparatus for estimating depth, comprising:
A non-transitory computer-readable medium having program code recorded thereon for estimating depth, the program code executed by a processor and comprising:
Dependencies are inferred from the claim text.