Abstract
Text-to-image generation powered by Diffusion Transformers (DiTs) has made remarkable strides, yet remote sensing (RS) synthesis lags behind due to two barriers: the absence of a domain-specialized DiT prior and the prohibitive cost of training at the large resolutions that RS applications demand. Training-free resolution promotion via Rotary Position Embedding (RoPE) rescaling offers a practical remedy, but every existing method applies a static positional scaling rule throughout the denoising process. This uniform compression is particularly harmful for RS imagery, whose substantially denser medium- and high-frequency energy encodes the fine structures critical for aerial-scene realism, such as vehicles, building contours, and road markings. Addressing both challenges requires a domain-specialized generative prior coupled with a denoising-aware positional adaptation strategy. To this end, we fine-tune FLUX on over 100,000 curated RS images to build a strong domain prior (RS-FLUX), and propose Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion (SHARP), a training-free method that introduces a rational fractional time schedule k_rs(t) into RoPE. SHARP applies strong positional promotion during the early layout-formation stage and progressively relaxes it during detail recovery, aligning extrapolation strength with the frequency-progressive nature of diffusion denoising. Its resolution-agnostic formulation further enables robust multi-scale generation from a single set of hyperparameters. Extensive experiments across six square and rectangular resolutions show that SHARP consistently outperforms all training-free baselines on CLIP Score, Aesthetic Score, and HPSv2, with widening margins at more aggressive extrapolation factors and negligible computational overhead. Code and weights are available at this https URL.
Abstract (translated)
基于扩散Transformer（DiT）的文生图技术已取得显著进展，但遥感（RS）图像合成仍面临两大瓶颈：缺乏领域专用的DiT先验模型，以及训练高分辨率RS应用所需模型的 prohibitive 成本。通过旋转位置嵌入（RoPE）重缩放实现的无训练分辨率提升提供了一种实用方案，但现有方法均在去噪全程采用静态位置缩放规则。这种均匀压缩对遥感图像尤为不利——其中高密度的中高频能量编码着对航拍场景真实性至关重要的精细结构（如车辆、建筑轮廓与道路标线）。要同时解决这两大挑战，需要领域专用的生成先验与感知去噪阶段的位置自适应策略。为此，我们在超过10万张精选遥感图像上微调FLUX模型，构建出强领域先验（RS-FLUX），并提出基于频谱感知的高动态自适应分辨率提升方法（SHARP）。该方法在RoPE中引入有理数分数时间调度k_rs(t)，在早期布局形成阶段施加强位置增强，并在细节恢复阶段逐步放松，使外推强度与扩散去噪的频率渐进特性相匹配。其分辨率无关的公式设计还能通过单一超参数集实现稳健的多尺度生成。在六种方形与矩形分辨率上的大量实验表明，SHARP在CLIP Score、美学评分与HPSv2指标上持续超越所有无训练基线方法，且在外推因子更激进时优势扩大，计算开销可忽略。代码与模型权重已公开于此https URL。
URL
https://arxiv.org/abs/2603.21783
