AI RESEARCH

Unlocking Dense Metric Depth Estimation in VLMs

arXiv CS.CV

ArXi:2605.15876v1 Announce Type: new Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and prevents the recovery of dense geometry. Prior methods either distill geometry from external vision models,