Detecting pose of 3d objects

A computer-implemented method of detecting pose of an object, the method comprising:

• receiving, at a processor, captured sensor data depicting the object;
• storing, at a memory, a model of a class of object of which the depicted object is a member, the model comprising a plurality of parameters specifying the pose, comprising global position and global orientation, of the model;
• and
• computing values of the parameters of the model by:
• calculating an optimization to fit the model to the captured sensor data, wherein the optimization comprises iterated computation of:
• updates to the values of the parameters and updates to values of variables representing correspondences between the captured sensor data and the model, the updates being interdependent in computation;
• and
• discarding updates to values of the variables representing correspondences without applying the discarded updates.

An apparatus for detecting pose of an object, the apparatus comprising:

• a processor configured to receive captured sensor data depicting the object;
• a memory storing a model of a class of object of which the depicted object is a member, the model comprising a plurality of components, and for each component a plurality of parameters specifying the pose, comprising global position and global orientation, of the model;
• the processor configured to compute values of the parameters of the model by calculating an optimization to fit the model to the captured sensor data, where variables representing correspondences between the captured sensor data and the model are included in the optimization jointly with the pose parameters;
• and wherein the processor is configured to compute the optimization separately for each component in parallel.