Method and apparatus with depth information estimation
AssigneeSamsung Electronics Co., Ltd.
InventorsJiwhan Kim, Sungjoo Suh, Minsu Ahn
Life of this patent
Estimating the term…
Abstract
A method of estimating depth information includes generating a first simulated image using a simulator provided with a first depth map, training an artificial neural network model based on the first depth map and the first simulated image, generating a second depth map by inputting an actual image into the trained artificial neural network model, and generating a second simulated image using the simulator provided with the second depth map.
Claims18
A processor-implemented method, the method comprising:
- generating a first simulated image using a simulator provided with a first depth map;
- training an artificial neural network model based on the first depth map and the first simulated image;
- generating a second depth map using the trained artificial neural network model provided with an actual image into the trained artificial neural network model;
- and
- generating a second simulated image using the simulator provided with the second depth map.
A processor-implemented method, the method comprising:
- generating a depth map corresponding to an actual image by inputting the actual image to an artificial neural network model,
- wherein the artificial neural network model is trained based on the depth map and a simulated image generated by using a simulator provided with the depth map.
An electronic apparatus comprising:
- a processor configured to:
- generate a first simulated image by inputting a first depth map into a simulator;
- train an artificial neural network model based on the first depth map and the first simulated image;
- generate a second depth map by inputting an actual image into the trained artificial neural network model;
- and
- generate a second simulated image by inputting the second depth map into the simulator.
An electronic apparatus comprising:
- a processor configured to:
- train an artificial neural network model based on a first depth map and a first simulated image generated using a simulator provided with the first depth map;
- and
- retrain the trained artificial neural network mode based on a second depth map, generated by the simulator provided with the trained artificial neural network model provided with a scanning electron microscope (SEM) image, and a second simulated image, generated by the simulator provided with the second depth map.
Dependencies are inferred from the claim text.