AI RESEARCH
Monocular Depth Estimation via Neural Network with Learnable Algebraic Group and Ring Structures
arXiv CS.CV
•
ArXi:2604.24328v1 Announce Type: new Monocular depth estimation (MDE) has witnessed remarkable progress driven by Convolutional Neural Networks and transformer-based architectures. However, these approaches typically treat the problem as a generic image-to-image regression on Euclidean grids, thereby overlooking the intrinsic algebraic and geometric structures induced by perspective projection.