Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency

Understand

Learning to reconstruct depths in a single image by watching unlabeled videos via deep convolutional network (DCN) is attracting significant attention in recent years.

• In this paper, we introduce a surface normal representation for unsupervised depth estimation framework.
• Our estimated depths are constrained to be compatible with predicted normals, yielding more robust geometry results.
• Specifically, we formulate an edge-aware depth-normal consistency term, and solve it by constructing a depth-to-normal layer and a normal-to-depth layer inside of the DCN.