dino

Researchers at the University of Pittsburgh used Meta's AI models SAM3 and DINO to help build one of the most advanced wheelchairs in the world.

PointDiT presents a minimalist pixel-space diffusion transformer using a plain ViT architecture for monocular geometry estimation, outperforming complex latent-based models while maintaining simplicity and robustness in ambiguous regions.

This paper introduces a post-training framework that leverages 3D priors from SAM3D to improve semantic correspondence in 2D foundation features, addressing issues like left-right confusion and repeated parts. The method uses instance-specific 3D reconstruction without pose annotations or spherical geometry shortcuts.

Researchers at the University of Pennsylvania are using AI models like DINO and SAM to automate and modernize medical triage in emergency response.