MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models

TL;DR

MapSR is a prompt-driven land cover map super-resolution framework that enhances low-resolution maps into high-resolution ones efficiently without extensive training, leveraging vision foundation models and minimal annotations.

Contribution

It introduces a novel prompt-driven approach that decouples supervision from training, significantly reducing computational costs and training time for high-resolution land cover mapping.

Findings

Achieves 59.64% mIoU without HR labels

Reduces training time from hours to minutes

Maintains competitive performance with weakly supervised methods

Abstract

High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations. We revisit this problem from the perspective of map super-resolution, which enhances coarse low-resolution (LR) land-cover products into HR maps at the resolution of the input imagery. Existing weakly supervised methods can leverage LR labels, but they typically use them to retrain dense predictors with substantial computational cost. We propose MapSR, a prompt-driven framework that decouples supervision from model training. MapSR uses LR labels once to extract class prompts from frozen vision foundation model features through a lightweight linear probe, after which HR mapping proceeds via training-free metric inference and graph-based prediction refinement. Specifically, class prompts are estimated by aggregating high-confidence HR features identified by the linear probe, and HR predictions are obtained by cosine-similarity matching followed by graph-based propagation for spatial refinement. Experiments on the Chesapeake Bay dataset show that MapSR achieves 59.64% mIoU without any HR labels, remaining competitive with the strongest weakly supervised baseline and surpassing a fully supervised baseline. Notably, MapSR reduces trainable parameters by four orders of magnitude and shortens training time from hours to minutes, enabling scalable HR mapping under limited annotation and compute budgets. The code is available at https://github.com/rikirikirikiriki/MapSR.