US 12,243,260 B2
Producing a depth map from a monocular two-dimensional image
Vitor Guizilini, Santa Clara, CA (US); Rares A. Ambrus, San Francisco, CA (US); Dian Chen, Mountain View, CA (US); Adrien David Gaidon, Mountain View, CA (US); and Sergey Zakharov, San Francisco, CA (US)
Assigned to Toyota Research Institute, Inc., Los Altos, CA (US); and Toyota Jidosha Kabushiki Kaisha, Toyota (JP)
Filed by Toyota Research Institute, Inc., Los Altos, CA (US)
Filed on Aug. 2, 2022, as Appl. No. 17/879,307.
Claims priority of provisional application 63/279,823, filed on Nov. 16, 2021.
Claims priority of provisional application 63/279,404, filed on Nov. 15, 2021.
Prior Publication US 2023/0154024 A1, May 18, 2023
Int. Cl. G06T 7/73 (2017.01); G06T 7/55 (2017.01); G06T 7/593 (2017.01)
CPC G06T 7/73 (2017.01) [G06T 7/55 (2017.01); G06T 7/593 (2017.01); G06T 2207/10012 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a first processor; and
a first memory storing:
a neural network, the neural network including:
a first encoding portion module including instructions that, when executed by the first processor, cause the first processor to encode an image to produce single-frame features;
a multi-frame feature matching portion module including instructions that, when executed by the first processor, cause the first processor to process the single-frame features to produce information; and
a decoding portion module including instructions that, when executed by the first processor, cause the first processor to decode the information to produce a depth map, wherein a first training dataset, used to train the multi-frame feature matching portion module, is different from a second training dataset used to train the encoding portion module and the decoding portion module.