SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis

• URL: http://arxiv.org/abs/2603.21783v1
• Date: Mon, 23 Mar 2026 10:25:45 GMT
• Title: SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis
• Abstract summary: Remote sensing imagery encodes fine structures critical for aerial-scene realism, such as vehicles, building contours, and road markings.<n>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.<n>We 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.
• Score: 14.489371802189426
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 https://github.com/bxuanz/SHARP.

Related papers

• Low-Depth and Noise-Resilient Quantum State Preparation for Partial Differential Equations via Virtual Rz [0.0]
  Exact state-preparation decompositions can reach unit fidelity ideally, but their two-qubit depth grows quickly and causes severe fidelity loss on NISQ hardware.<n>We propose a low-depth, hardware-aware variational ansatz tailored to smooth, weakly entangled, near-real target distributions typical of damped PDE dynamics.<n>Results indicate that virtual-Rz-enabled, low-depth circuits provide a practical, noise-resilient state-preparation primitive for PDE solvers on NISQ and early FTQC hardware.
  arXiv  Detail & Related papers  (2026-08-18T01:11:10Z)
• MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution [50.60539317126614]
  MeanSR learns an LR-conditioned average velocity field to directly capture the finite-time transition from noisy inputs to plausible HR outputs.<n>Experiments show that MeanSR outperforms CTMSR on CLIPIQA, MUSIQ, and MANIQA while substantially reducing FLOPs and inference latency.
  arXiv  Detail & Related papers  (2026-08-10T10:33:18Z)
• TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution [52.96050253456634]
  TRaM-VSR is a framework for adaptive token allocation using context-aware video priors and network-levels.<n>It is shown that TRaM-VSR accelerates inference significantly while preserving state-of-the-art reconstruction quality and robust temporal consistency.
  arXiv  Detail & Related papers  (2026-07-24T11:57:26Z)
• AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution [31.274516936914267]
  Diffusion models have significantly advanced video super-resolution (VSR) but remain largely constrained to fixed upsampling scales.<n>We propose AVSR-Diff, a novel decoupled framework that separates scale-a latent denoising from continuous coordinate rendering.<n>Our framework consistently preserves high-frequency details and strong temporal stability across various scales, surpassing state-of-the-art arbitrary-scale baselines.
  arXiv  Detail & Related papers  (2026-07-01T14:22:22Z)
• Flow-based Gaussian Splatting for Continuous-Scale Remote Sensing Image Super-Resolution [5.111440805874026]
  FlowGS is a generative reconstruction framework for arbitrary-scale SR of RSIs.<n>We employ 2D Gaussian splatting to construct a continuous feature field, thereby enabling flexible reconstruction at arbitrary query locations.
  arXiv  Detail & Related papers  (2026-05-21T08:19:09Z)
• ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models [52.648413887350195]
  We propose Stage-Aware RoPE Remapping to suppress global repetition, local repetition, and detail degradation.<n>We also propose Entropy-Driven Adaptive Attention, which quantifies dispersion via a resolution-invariant normalized entropy.<n>Our method consistently outperforms prior resolution-extrapolation methods in both structural coherence and fine-detail fidelity.
  arXiv  Detail & Related papers  (2026-05-11T06:14:38Z)
• Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compression [28.21479870337623]
  ASSR-EIC is a novel image compression framework that supports variable-rate extreme image compression.<n>We exploit the compression- and rescaling-aware diffusion prior to guide the reconstruction, yielding high fidelity and high realism restoration.
  arXiv  Detail & Related papers  (2026-03-18T06:35:53Z)
• Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement [89.99237142387655]
  We introduce LH-VAE, which enhances semantic robustness through visual semantic constraints and progressive degradations.<n>Latent Harmony is a two-stage framework that redefines VAEs for UHD restoration by jointly regularizing the latent space and enforcing high-frequency-aware reconstruction.<n>Experiments show Latent Harmony achieves state-of-the-art performance across UHD and standard-resolution tasks, effectively balancing efficiency, perceptual quality, and reconstruction accuracy.
  arXiv  Detail & Related papers  (2025-10-09T08:54:26Z)
• FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution [70.61549422952193]
  Face super-resolution (FSR) under limited computational costs remains an open problem.<n>Existing approaches typically treat all facial pixels equally, resulting in suboptimal allocation of computational resources.<n>We propose FADPNet, a Frequency-Aware Dual-Path Network that decomposes facial features into low- and high-frequency components.
  arXiv  Detail & Related papers  (2025-06-17T02:33:42Z)
• AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution [50.584551250242235]
  AdaptSR is a low-rank adaptation framework that efficiently repurposes bi-cubic-trained SR models for real-world tasks.<n>Our experiments demonstrate that AdaptSR outperforms GAN and diffusion-based SR methods by up to 4 dB in PSNR and 2% in perceptual scores on real SR benchmarks.
  arXiv  Detail & Related papers  (2025-03-10T18:03:18Z)
• WaveDiffUR: A diffusion SDE-based solver for ultra magnification super-resolution in remote sensing images [2.7830219396433704]
  We introduce WaveDiffUR, a novel wavelet-domain diffusion UR solver that decomposes the UR process into sequential sub-processes addressing conditional wavelet components.<n>WaveDiffUR iteratively reconstructs low-frequency wavelet details (ensuring global consistency) and high-frequency components (enhancing local fidelity) by incorporating pre-trained SR models as plug-and-play modules.<n>To address limitations in fixed boundary conditions at extreme magnifications, we introduce the cross-scale pyramid (CSP) framework.
  arXiv  Detail & Related papers  (2024-12-25T22:26:39Z)
• HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging [138.04956118993934]
  We propose a high-resolution dual-domain learning network (HDNet) for HSI reconstruction. On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features. On the other hand, frequency domain learning (FDL) is introduced for HSI reconstruction to narrow the frequency domain discrepancy.
  arXiv  Detail & Related papers  (2022-03-04T06:37:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.