Abstract: A patient model for mapping a set of pose parameters and a set of shape parameters onto a surface grid is provided. Patient image data that represents a spine of a patient is provided, and a patient-specific set of pose parameters and a patient-specific set of shape parameters are determined based on the patient image data. An initial surface grid that represents the spine in an initial state with spine curvature is calculated. The calculation includes applying the patient model to the patient-specific set of pose parameters and the patient-specific set of shape parameters. A target surface grid that represents the spine of the patient in a target state with a straightened spine is provided. By comparing the target surface grid with the initial surface grid, a displacement field for the spine is determined and, depending on the displacement field, support information is generated and displayed visually.

Abstract: A 3D mesh of a person shall be reconstructed based on one single 2D image. For this purpose, 2D vertex projections and 3D vertex projections of the person are predicted based on the single 2D image. An approximated pose is estimated from the 3D vertex projections. The shape and/or pose, i.e. the 3D mesh of the person, is computed from the predicted 2D vertex projections and from the approximated pose by using a pregiven camera model and an articulated 3D mesh model of a human body.