Abstract: A computer-implemented method for generating labelled training images characterizing manipulation of a plurality of stackable objects in a workspace. The method includes: obtaining a first training image subset obtained at a first time index comprising a depth map and a visual image of a plurality of stackable objects in a stacking region of a workspace; obtaining a second training image subset obtained at a second time index comprising a depth map and a visual image of the stacking region in the workspace, wherein the second training image subset characterizes a changed spatial state of the stacking region; computing a depth difference mask based on the depth maps; computing a visual difference mask based on the visual images of the first and second training image subsets; generating an annotated segmentation mask using the depth difference mask and/or the visual difference mask.

Abstract: A computer-implemented method for providing training data for training of a data-driven depth completion model as a machine-learning model, wherein the depth completion model is to be trained to generate dense depth maps from sensor acquired raw depth maps. The method includes: providing multiple synthetic dense depth map data items from CAD data of various synthetic scenes; providing multiple real raw depth map data items obtained from real-world depth sensor measurements of real-world scenes; training a generative model for obtaining a trained generator model for generating generated raw depth map data items from the synthetic dense depth map data items; applying the trained generator model to generate training data from provided synthetic dense depth map data.