Depth extraction

A training computer system comprising:

• an input configured to receive a set of training examples, each training example comprising (i) a stereo image pair and (ii) an estimated disparity map computed from at least one image of the stereo image pair by a depth estimator;
• one or more processors;
• and
• memory configured to hold executable instructions which cause the one or more processors, when executed thereon, to:
• execute a training process to learn one or more uncertainty estimation parameters of a perturbation function, the uncertainty estimation parameters for estimating uncertainty in disparity maps computed by the depth estimator;
• wherein the training process is performed by sampling a likelihood function based on the training examples and the perturbation function, thereby obtaining a set of sampled values for learning the one or more uncertainty estimation parameters;
• wherein the likelihood function measures similarity between one image of each training example and a reconstructed image computed by transforming the other image of that training example based on a possible true disparity map derived from the estimated disparity map of that training example and the perturbation function.

A computer program product comprising executable code embodied in a non-transitory computer-readable storage medium which is configured, when executed on one or more processors, to implement operations comprising:

• receiving a set of training examples, each training example comprising (i) a stereo image pair and (ii) an estimated disparity map computed from at least one image of the stereo image pair by a depth estimator;
• and
• executing a training process to learn one or more uncertainty estimation parameters of a perturbation function, the uncertainty estimation parameters for estimating uncertainty in disparity maps computed by the depth estimator;
• wherein the training process is performed by sampling a likelihood function based on the training examples and the perturbation function, thereby obtaining a set of sampled values for learning the one or more uncertainty estimation parameters;
• and
• wherein the likelihood function measures similarity between one image of each training example and a reconstructed image computed by transforming the other image of that training example based on a possible true disparity map derived from the estimated disparity map of that training example and the perturbation function.