用自监督学习+扩散模型，让卫星图像预测更清晰准确。
Sat-JEPA-Diff: Bridging Self-Supervised Learning and Generative Diffusion for Remote Sensing
- 用IJEPA提取稳定语义特征，再通过轻量适配器引导扩散模型
- 在哨兵2号数据上实现0.8984的GSSIM和0.1475的FID，边界更锐利
- 适合需要高精度结构与真实纹理的遥感预测任务
卫星影像预测需兼顾结构准确性与纹理细节。传统确定性方法（如PredRNN或SimVP）虽降低像素误差，但存在“回归均值”问题，导致输出模糊，掩盖细微地理空间特征；生成模型虽能提供逼真纹理，却常引入结构异常。为此，我们提出Sat-JEPA-Diff，结合自监督学习（SSL）与隐式扩散模型（LDM）。其IJEPA模块预测稳定语义表示，并通过轻量级交叉注意力适配器引导冻结的Stable Diffusion主干网络。确保合成的高保真纹理严格基于精确的结构预测。在全局哨兵-2号数据集上评估，Sat-JEPA-Diff显著提升边缘锐度，感知评分达GSSIM: 0.8984、FID: 0.1475，远超确定性基线，且在标准自回归稳定性限制下表现优异。代码与数据集已开源。
原文摘要 · Abstract (English)
Predicting satellite imagery requires a balance between structural accuracy and textural detail. Standard deterministic methods like PredRNN or SimVP minimize pixel-based errors but suffer from the "regression to the mean" problem, producing blurry outputs that obscure subtle geographic-spatial features. Generative models provide realistic textures but often misleadingly reveal structural anomalies. To bridge this gap, we introduce Sat-JEPA-Diff, which combines Self-Supervised Learning (SSL) with Hidden Diffusion Models (LDM). An IJEPA module predicts stable semantic representations, which then route a frozen Stable Diffusion backbone via a lightweight cross-attention adapter. This ensures that the synthesized high-accuracy textures are based on absolutely accurate structural predictions. Evaluated on a global Sentinel-2 dataset, Sat-JEPA-Diff excels at resolving sharp boundaries. It achieves leading perceptual scores (GSSIM: 0.8984, FID: 0.1475) and significantly outperforms deterministic baselines, despite standard autoregressive stability limits. The code and dataset are publicly available on https://github.com/VU-AIML/SAT-JEPA-DIFF.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。