Karlo Koledić — accepted AI-conference papers

2025

GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion

Karlo Koledić, Luka Petrović, Ivan Marković, Ivan Petrović

ICCV 2025poster

Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature, while the entanglement between camera parameters and depth amplifies issues further, hindering multi-dataset training and zero-shot accuracy. This challenge is particularly evident in autonom…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

MOFT: Monocular odometry based on deep depth and careful feature selection and tracking

Karlo Koledić, Igor Cvišić, Ivan Marković, Ivan Petrović

ICRA 2023poster

Autonomous localization in unknown environments is a fundamental problem in many emerging fields and the monocular visual approach offers many advantages, due to being a rich source of information and avoiding comparatively more complicated setups and multisensor calibration. Deep learning opened ne…

Cited by 7 Source ↗Scholar ↗