AI Paper Atlas

Research map / Image generation / Image restoration

MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation

Zhiping Yu, Chenyang Liu, Liqin Liu, Zhenwei Shi, Zhengxia Zou

TPAMI 2024 · Image generation › Image restoration · approach: Efficient restoration architectures · 67 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add spatial resolution guidance (ablation)MetaEarth · Generated 64m images, all regionsFID: 27.79 -> 23.97Improved
add spatial resolution guidance (ablation)MetaEarth · Generated 16m images, all regionsFID: 16.00 -> 15.12Improved
add spatial resolution guidance (ablation)MetaEarth · Generated 4m images, all regionsFID: 13.43 -> 13.32Improved
add spatial resolution guidance (ablation)MetaEarth · Generated 4m* images, all regionsFID: 92.61 -> 84.75Improved
add spatial resolution guidance (ablation)MetaEarth · Generated 64m images, Southern HemisphereFID: 42.11 -> 44.16Hurt
add spatial resolution guidance (ablation)MetaEarth · Generated 16m images, Southern HemisphereFID: 25.50 -> 27.76Hurt
add overlapped sliding window (ablation)MetaEarth · Seam gradientAverage directional gradient: 24.67 -> 17.88Improved
add noise sampling constraint on top of overlap (ablation)MetaEarth · Seam gradientAverage directional gradient: 17.88 -> 12.58Improved
add high-order degradation in training (ablation)MetaEarth · 16m to 4m generationFID: 148.31 -> 78.72Improved
use self-cascaded generation instead of direct 256m to 4m generation (ablation)MetaEarth · 4m 1024x1024 generationvisual qualityImproved
add MetaEarth-generated augmentation data (5x)VGG19 · 7-class remote sensing classificationaccuracy: 95.72 -> 97.28Improved
add MetaEarth-generated augmentation data (5x)ResNet34 · 7-class remote sensing classificationaccuracy: 96.11 -> 99.22Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy