Spectral-Structured Diffusion for Single-Image Rain Removal

• URL: http://arxiv.org/abs/2603.09054v1
• Date: Tue, 10 Mar 2026 00:53:47 GMT
• Title: Spectral-Structured Diffusion for Single-Image Rain Removal
• Abstract summary: We introduce SpectralDiff, a spectral-structured diffusion-based framework tailored for single-image rain removal.<n>Our method incorporates structured spectral perturbations to guide the progressive suppression of multi-directional rain components.
• Score: 5.382951136630937
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rain streaks manifest as directional and frequency-concentrated structures that overlap across multiple scales, making single-image rain removal particularly challenging. While diffusion-based restoration models provide a powerful framework for progressive denoising, standard spatial-domain diffusion does not explicitly account for such structured spectral characteristics. We introduce SpectralDiff, a spectral-structured diffusion-based framework tailored for single-image rain removal. Rather than redefining the diffusion formulation, our method incorporates structured spectral perturbations to guide the progressive suppression of multi-directional rain components. To support this design, we further propose a full-product U-Net architecture that leverages the convolution theorem to replace convolution operations with element-wise product layers, improving computational efficiency while preserving modeling capacity. Extensive experiments on synthetic and real-world benchmarks demonstrate that SpectralDiff achieves competitive rain removal performance with improved model compactness and favorable inference efficiency compared to existing diffusion-based approaches.

Related papers

• Revisiting Spectral Representations in Generative Diffusion Models [98.43552218868837]
  Diffusion models have shown remarkable performance on diverse generation tasks.<n>Recent work finds that imposing representation alignment on the hidden states of diffusion networks can both facilitate training convergence and enhance sampling quality.<n>We investigate the connection between self-supervised spectral representation learning and diffusion generative models through a shared perspective on perturbation kernels.
  arXiv  Detail & Related papers  (2026-09-08T04:54:02Z)
• Multiscale Hypersonic Boundary Layer Reconstruction via Spectral Binning and Subdomain-wise Conditional Diffusion [1.689433487573205]
  We propose a multiscale probabilistic reconstruction framework for hypersonic Couette flow.<n>Near-wall states are inferred from limited top-wall observations using conditional diffusion model.<n>A soft overlap inpainting strategy assembles subdomain predictions into full-volume reconstructions.
  arXiv  Detail & Related papers  (2026-06-12T23:40:01Z)
• SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation [10.518150741228862]
  SlimDiffSR is a lightweight and efficient diffusion-based framework for real-world remote sensing image super-resolution.<n>It attains up to $200times$ inference acceleration and a $20times$ reduction in model parameters compared with multi-step diffusion models.
  arXiv  Detail & Related papers  (2026-05-04T03:54:54Z)
• High-Dimensional Noise to Low-Dimensional Manifolds: A Manifold-Space Diffusion Framework for Degraded Hyperspectral Image Classification [14.798241863302438]
  In real-world remote sensing scenarios, the superposition of multiple degradation factors disrupts intrinsic manifold structure.<n>This paper proposes a manifold-space diffusion framework (MSDiff) for robust hyperspectral classification under complex degradation conditions.
  arXiv  Detail & Related papers  (2026-04-29T04:20:42Z)
• Spectral Regularization for Diffusion Models [14.919876123456747]
  We propose a loss-level spectral regularization framework that augments standard diffusion training with differentiable Fourier- and wavelet-domain losses.<n>Our approach is compatible with DDPM, DDIM, and EDM formulations and introduces negligible computational overhead.
  arXiv  Detail & Related papers  (2026-03-02T22:39:02Z)
• Generative Modeling of Aerosol State Representations [5.772617906251992]
  Aerosol-cloud-radiation interactions remain among the most uncertain components of the Earth's climate system.<n>We present a framework for learning deep variational autoencoder models of speciated mass and number concentration distributions.<n>By compressing hundreds of original dimensions into ten latent variables, the approach enables efficient storage and processing.
  arXiv  Detail & Related papers  (2025-10-11T22:38:30Z)
• OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot [4.990334603434127]
  OBS-Diff is a novel one-shot pruning framework that enables accurate and training-free compression of large-scale text-to-image diffusion models.<n>Extensive experiments show that OBS-Diff achieves state-of-the-art one-shot pruning for diffusion models, delivering inference acceleration with minimal degradation in visual quality.
  arXiv  Detail & Related papers  (2025-10-08T08:19:15Z)
• FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution [48.88184541515326]
  We propose a simple and effective method, named FaithDiff, to fully harness the power of latent diffusion models (LDMs) for faithful image SR.<n>In contrast to existing diffusion-based SR methods that freeze the diffusion model pre-trained on high-quality images, we propose to unleash the diffusion prior to identify useful information and recover faithful structures.
  arXiv  Detail & Related papers  (2024-11-27T23:58:03Z)
• Distilling Diffusion Models into Conditional GANs [90.76040478677609]
  We distill a complex multistep diffusion model into a single-step conditional GAN student model. For efficient regression loss, we propose E-LatentLPIPS, a perceptual loss operating directly in diffusion model's latent space. We demonstrate that our one-step generator outperforms cutting-edge one-step diffusion distillation models.
  arXiv  Detail & Related papers  (2024-05-09T17:59:40Z)
• Global Structure-Aware Diffusion Process for Low-Light Image Enhancement [64.69154776202694]
  This paper studies a diffusion-based framework to address the low-light image enhancement problem. We advocate for the regularization of its inherent ODE-trajectory. Experimental evaluations reveal that the proposed framework attains distinguished performance in low-light enhancement.
  arXiv  Detail & Related papers  (2023-10-26T17:01:52Z)
• Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
  Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
  arXiv  Detail & Related papers  (2023-06-01T03:08:28Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)

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.