Depth completion using attention-based refinement of features

An apparatus configured to generate depth information from one or more images, the apparatus comprising:

• one or more memories configured to store the one or more images;
• and
• one or more processors coupled to the one or more memories, the one or more processors being configured to:
• obtain a first depth map corresponding to an input comprising an image of the one or more images and a sparse depth measurement;
• generate a three-dimensional (3D) point cloud based on the first depth map and multi-scale visual features of the input, wherein the 3D point cloud includes a plurality of 3D point features uplifted from the multi-scale visual features;
• process at least a portion of the plurality of 3D point features using one or more self-attention layers to generate refined 3D point features;
• generate a two-dimensional (2D) projection of the refined 3D point features;
• and
• generate a second depth map based on the 2D projection of the refined 3D point features.