Information processing apparatus, information processing method, and program

An information processing apparatus comprising:

• an acquiring unit configured to acquire first data and second data from input data;
• a deriving unit configured to derive gradient data representing a gradient of correspondence data representing a correlation between partial data of the first data and partial data of the second data based on neighborhood correspondence data, wherein the gradient derives from difference in distribution of correlation;
• an evaluation unit configured to evaluate degree of coincidence between the partial data of the first data and the partial data of the second data;
• and
• a propagating unit configured to propagate the correspondence data in accordance with the gradient data and to replace the correspondence data with neighborhood correspondence data which exists in a neighborhood on the distribution in a case where the degree of coincidence between the partial data of the first data and the partial data of the second data which has derived the neighborhood correspondence data is larger than the degree of coincidence between the partial data of the first data and the partial data of the second data which has derived the correspondence data.

An information processing method comprising:

• acquiring first data and second data;
• gradient data representing a gradient of correspondence data representing a correlation between partial data of the first data and partial data of the second data based on neighborhood correspondence data, wherein the gradient derives from difference in distribution of correlation;
• evaluating degree of coincidence between the partial data of the first data and the partial data of the second data;
• and
• propagating the correspondence data in accordance with the gradient data and to replace the correspondence data with neighborhood correspondence data which exists in a neighborhood on the distribution in a case where the degree of coincidence between the partial data of the first data and the partial data of the second data which has derived the neighborhood correspondence data is larger than the degree of coincidence between the partial data of the first data and the partial data of the second data which has derived the correspondence data.

An information processing method comprising:

• acquiring first data and second data from input data;
• deriving gradient data representing a gradient of correspondence data representing a correlation between partial data of the first data and partial data of the second data based on neighborhood correspondence data, wherein the gradient derives from difference in distribution of correlation;
• evaluating degree of coincidence between the partial data of the first data and the partial data of the second data;
• and
• propagating the correspondence data in accordance with the gradient data and to replace the correspondence data with neighborhood correspondence data which exists in a neighborhood on the distribution in a case where the degree of coincidence between the partial data of the first data and the partial data of the second data which has derived the neighborhood correspondence data is larger than the degree of coincidence between the partial data of the first data and the partial data of the second data which has derived the correspondence data.