AI RESEARCH
Another BRIXEL in the Wall: Towards Cheaper Dense Features
arXiv CS.LG
•
ArXi:2511.05168v2 Announce Type: replace-cross Vision foundation models achieve strong performance on both global and locally dense downstream tasks. Pretrained on large images, the recent DINOv3 model family is able to produce very fine-grained dense feature maps, enabling state-of-the-art performance. However, computing these feature maps requires the input image to be available at very high resolution, as well as large amounts of compute due to the squared complexity of the transformer architecture.