3 papers
cs.CV2025
EGSA-PT:Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objects
Gbenga Omotara, Ramy Farag, Seyed Mohamad Ali Tousi +1
Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has expl…
cs.CV2025
The Fourth Monocular Depth Estimation Challenge
Anton Obukhov, Matteo Poggi, Fabio Tosi +54
This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a…
cs.CV2025
A Zero-Shot Learning Approach for Ephemeral Gully Detection from Remote Sensing using Vision Language Models
Seyed Mohamad Ali Tousi, Ramy Farag, Jacket Demby's +3
Ephemeral gullies are a primary cause of soil erosion and their reliable, accurate, and early detection will facilitate significant improvements in the sustainability of global agr…