Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion
Karlo KolediÄ, Luka PetroviÄ, Ivan MarkoviÄ +1
Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature, while the entanglement between camera parameters and depth amplifies is…
cs.CV2025
An Active Inference Model of Covert and Overt Visual Attention
Tin MiÅ¡iÄ, Karlo KolediÄ, Fabio Bonsignorio +2
The ability to selectively attend to relevant stimuli while filtering out distractions is essential for agents that process complex, high-dimensional sensory input. This paper intr…