Invention Grant
- Patent Title: Multi-scale recurrent decoder for monocular depth estimation
-
Application No.: US17555112Application Date: 2021-12-17
-
Publication No.: US11756219B2Publication Date: 2023-09-12
- Inventor: Vitor Guizilini , Adrien David Gaidon
- Applicant: TOYOTA RESEARCH INSTITUTE, INC.
- Applicant Address: US CA Los Altos
- Assignee: TOYOTA RESEARCH INSTITUTE, INC.
- Current Assignee: TOYOTA RESEARCH INSTITUTE, INC.
- Current Assignee Address: US CA Los Altos
- Agency: SEYFARTH SHAW LLP
- Main IPC: G06T7/00
- IPC: G06T7/00 ; G06T7/50 ; G06T3/40

Abstract:
A method for using an artificial neural network associated with an agent to estimate depth, includes receiving, at the artificial neural network, an input image captured via a sensor associated with the agent. The method also includes upsampling, at each decoding layer of a plurality of decoding layers of the artificial neural network, decoded features associated with the input image to a resolution associated with a final output of the artificial neural network. The method further includes concatenating, at each decoding layer, the upsampled decoded features with features obtained at a convolution layer associated with a respective decoding layer. The method still further includes estimating, at a recurrent module of the artificial neural network, a depth of the input image based on receiving the concatenated upsampled decoded features from each decoding layer. The method also includes controlling an action of an agent based on the depth estimate.
Public/Granted literature
- US20220108463A1 MULTI-SCALE RECURRENT DECODER FOR MONOCULAR DEPTH ESTIMATION Public/Granted day:2022-04-07
Information query