Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration

Computer VisionarXiv:2605.00310PDF

Publish this paper in The AIPR Journal

Are you an author? Turn this AI review into a permanent, citable journal entry with a cover, open comments, and Scholar metadata.

Not the corresponding author? Request this paper

AIPR assessment

Problem difficulty: high. Remote-sensing SR is a crowded, mature area with many strong baselines, and the paper is trying to change the evaluation target itself rather than just win on PSNR. The strengths reinforce each other well: the large-scale aligned dataset, the downstream-task protocol, the open artifacts, and the broad model sweep together make the benchmark credible and immediately useful. The weaknesses also interact: the construction choices are partly heuristic, the downstream gains

Abstract

Super-resolution (SR) techniques have made major advances in reconstructing high-resolution images from low-resolution inputs. The increased resolution provides visual enhancement and utility for monitoring tasks. In particular, SR has been increasingly developed for satellite-based Earth observation, with applications in urban planning, agriculture, ecology, and disaster response. However, existing SR studies and benchmarks typically use fidelity metrics such as PSNR or SSIM, whereas the true utility of super-resolved images lies in supporting downstream tasks such as land cover classification, biomass estimation, and change detection. To bridge this gap, we introduce GeoSR-Bench, a downstream task-integrated SR benchmark dataset to evaluate SR models beyond fidelity metrics. GeoSR-Bench comprises spatially co-located, temporally aligned, and quality-controlled image pairs from about 36,000 locations across diverse land covers, spanning resolutions from 500m to 0.6m. To the best of our knowledge, GeoSR-Bench is the first SR benchmark that directly connects improved image resolution from SR models with downstream Earth monitoring tasks, including land cover segmentation, infrastructure mapping, and biophysical variable estimation. Using GeoSR-Bench, we benchmark GAN, transformer, neural operator, and diffusion-based SR models on perceptual quality and downstream task performance. We conduct experiments with 270 settings, covering 2 cross-platform SR tasks, 9 SR models, 3 downstream task models, and 5 downstream tasks for each SR task. The results show that improvements in traditional SR metrics often do not correlate with gains in task performance, and the correlations can be negative, indicating that these metrics provide limited guidance for selecting superior models for downstream tasks. This reveals the need to integrate downstream tasks into SR model development and evaluation.

Score Breakdown

Holistic Impression
83
Novelty
83
Rigor
78
Applicability
85
Clarity
84
Citation
77
Confidence: 85%

More from this week

More in Computer Vision