Vision requires a reference frame. To what extent does this reference frame depend on the structure of the visual input, rather than just on retinal landmarks? This question is particularly relevant ...

I go to books when I need to stimulate my imagination. Books never fail. I am a visual thinker, even when I write words, so I especially respond to visual books full of images, graphs, and pictures.

Abstract: In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Any-thing Model (SAM) to utilize annotated reference images as prompts for segmentation, ...