AI RESEARCH
DINOv3 Visual Representations for Blueberry Perception Toward Robotic Harvesting
arXiv CS.CV
•
ArXi:2603.02419v2 Announce Type: replace Vision Foundation Models trained via large-scale self-supervised learning have nstrated strong generalization in visual perception; however, their practical role and performance limits in agricultural settings remain insufficiently understood. This work evaluates DINOv3 as a frozen backbone for blueberry robotic harvesting-related visual tasks, including fruit and bruise segmentation, as well as fruit and cluster detection.