两篇新研究论文介绍了用于图像生成任务的高级扩散 Transformer 模型。第一篇 TerraDiT 专注于生成具有点状控制的卫星图像，为像素级地图提供了更丰富的语义和更友好的标注替代方案。第二篇 DS-DiT 通过解耦 Siamese 扩散 Transformer 架构中低分辨率图像和参考图像之间的交互，解决了遥感图像超分辨率问题，提高了细节恢复和视觉保真度。 AI
影响 这些论文展示了扩散 Transformer 架构在专业图像生成任务方面的进步，有望改进遥感分析和数据合成。
排序理由 两篇在 arXiv 上发表的学术论文，详细介绍了用于图像合成和超分辨率的新型扩散 Transformer 模型。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
TerraDiT-Ω generates satellite imagery from native geospatial primitives using Geometry-Aware Local Attention, enabling flexible conditioning and improved downstream geospatial tasks.
arXiv:2603.02172v2 Announce Type: replace Abstract: We introduce TerraDiT, a diffusion transformer designed for text-to-satellite image generation with point-based control. Existing controlled satellite image generative models often require pixel-level maps that are time-consumin…
arXiv:2605.17980v2 Announce Type: replace Abstract: Diffusion-based methods demonstrate significant potential for remote sensing image super-resolution at large scaling factors, particularly in reference-based super-resolution (RefSR), where high-resolution reference images provi…