FeatUp: A Model-Agnostic Framework for Features at Any Resolution

arXiv:2403.10516v1 Announce Type: cross
Abstract: Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime. However, these features often lack the spatial resolution to directly perform dense prediction tasks like segmentation and depth prediction because models aggressively pool information over large areas. In this work, we introduce FeatUp, a task- and model-agnostic framework to restore lost spatial information in deep features. We introduce …

abstract arxiv community computer computer vision cs.ai cs.cv cs.ir cs.lg enabling features few-shot framework however image model-agnostic prediction research segmentation semantics solve spatial tasks type vision vision research