Several examples describe techniques for aligning shapes using
pose information for
AI systems and applications. The systems and methods described here can use one or more pipelines configured to align shapes, such as three-dimensional shapes, using the shapes' poses. In some examples, training images to identify the poses, along with ground-truth poses associated with the training images, can be used to
train a
machine learning model. During and / or after training, the
machine learning model can then be used to process additional images to identify poses of additional shapes. In some examples, a
pose associated with a shape may include a gravity orientation and / or an
azimuth orientation of the shape, as represented by an image.These poses can then be used to align the additional forms, such as in relation to a canonical
pose.