Photometric Cost Volumes For Self-Supervised Depth Estimation
AssigneesToyota Research Institute, Inc., Toyota Jidosha Kabushiki Kaisha
InventorsVitor Guizilini, Rares A. Ambrus, Sergey Zakharov
Life of this patent
Estimating the term…
Loading patent…
AssigneesToyota Research Institute, Inc., Toyota Jidosha Kabushiki Kaisha
InventorsVitor Guizilini, Rares A. Ambrus, Sergey Zakharov
Estimating the term…
System, methods, and other embodiments described herein relate to an improved approach to training a depth model to derive depth estimates from monocular images using cost volumes. In one embodiment, a method includes predicting, using a depth model, depth values from at least one input image that is a monocular image. The method includes generating a cost volume by sampling the depth values corresponding to bins of the cost volume. The method includes determining loss values for the bins of the cost volume. The method includes training the depth model according to the loss values of the cost volume.
A depth system, comprising:
A non-transitory computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to:
A method, comprising:
Dependencies are inferred from the claim text.