Deep Spectral Prior

• URL: http://arxiv.org/abs/2505.19873v1
• Date: Mon, 26 May 2025 12:00:37 GMT
• Title: Deep Spectral Prior
• Abstract summary: We introduce Deep Spectral Prior (DSP), a new formulation of Deep Image Prior (DIP) that redefines image reconstruction as a frequency-domain alignment problem.<n>This shift introduces an explicit inductive bias towards spectral coherence, aligning with the known frequency structure of images and the spectral bias of convolutional neural networks.<n>We show that DSP naturally projects reconstructions onto a frequency-consistent manifold, enhancing interpretability and robustness.
• Score: 27.0616671887139
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce Deep Spectral Prior (DSP), a new formulation of Deep Image Prior (DIP) that redefines image reconstruction as a frequency-domain alignment problem. Unlike traditional DIP, which relies on pixel-wise loss and early stopping to mitigate overfitting, DSP directly matches Fourier coefficients between the network output and observed measurements. This shift introduces an explicit inductive bias towards spectral coherence, aligning with the known frequency structure of images and the spectral bias of convolutional neural networks. We provide a rigorous theoretical framework demonstrating that DSP acts as an implicit spectral regulariser, suppressing high-frequency noise by design and eliminating the need for early stopping. Our analysis spans four core dimensions establishing smooth convergence dynamics, local stability, and favourable bias-variance tradeoffs. We further show that DSP naturally projects reconstructions onto a frequency-consistent manifold, enhancing interpretability and robustness. These theoretical guarantees are supported by empirical results across denoising, inpainting, and super-resolution tasks, where DSP consistently outperforms classical DIP and other unsupervised baselines.

Related papers

• Calibrated Harmonic Overlaid Implicit Neural Representations for Multi-Dimensional Data [4.417873435160498]
  Implicit neural representation (INR) has emerged as a powerful prior for multi-dimensional data.<n>We propose a novel Calibrated Harmonic Overlaid Implicit Representation (CHOIR)<n>Our method achieves superior performance over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-06-25T08:48:31Z)
• Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Super-Resolution for Snapshot Compressive Imaging [79.35520607451187]
  We propose Phy-CoSF, which synergizes deep unfolding networks with implicit neural representations.<n>Specifically, we propose a two-phase architecture that bridges discrete-wavelength training with continuous spectral rendering.
  arXiv  Detail & Related papers  (2026-05-13T14:17:02Z)
• Oscillating Dispersion for Maximal Light-throughput Spectral Imaging [26.318289715715924]
  Oscillating Dispersion Imaging Spectrometer (ODIS) achieves near-full light throughput by axially translating a disperser between the conjugate image plane and a defocused position.<n> PAN-guided Dispersion-Aware Deep Unfolding Network (PDAUN) recovers high-fidelity spectral information from maskless dispersion.<n> experiments show state-of-the-art performance on standard benchmarks, and cross-system comparisons confirm that ODIS yields decisive gains under low illumination.
  arXiv  Detail & Related papers  (2026-03-16T14:34:06Z)
• Amortized Spectral Kernel Discovery via Prior-Data Fitted Network [0.0]
  We introduce an interpretability-driven framework for amortized spectral discovery from pre-trained PFNs with decoupled attention.<n>We propose decoder architectures that map PFN latents to explicit spectral density estimates and corresponding stationary kernels.<n>This yields orders-of-magnitude reductions in inference time compared to optimization-based baselines.
  arXiv  Detail & Related papers  (2026-01-29T13:51:26Z)
• Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution [75.3690742776891]
  We propose Iterative Diffusion Inference-Time Scaling with Adaptive Frequency Steering (IAFS)<n>IAFS addresses the challenge of balancing perceptual quality and structural fidelity by progressively refining the generated image through iterative correction of structural deviations.<n>Experiments show that IAFS effectively resolves the perception-fidelity conflict, yielding consistently improved perceptual detail and structural accuracy, and outperforming existing inference-time scaling methods.
  arXiv  Detail & Related papers  (2025-12-29T15:09:20Z)
• The Procrustean Bed of Time Series: The Optimization Bias of Point-wise Loss [53.542743390809356]
  This paper aims to provide a first-principles analysis of the Expectation of Optimization Bias (EOB)<n>Our analysis reveals a fundamental paradigm paradox: the more deterministic and structured the time series, the more severe the bias by point-wise loss function.<n>We present a concrete solution that simultaneously achieves both principles via DFT or DWT.
  arXiv  Detail & Related papers  (2025-12-21T06:08:22Z)
• SFP: Real-World Scene Recovery Using Spatial and Frequency Priors [84.27251794411673]
  Scene recovery serves as a critical task for various computer vision applications.<n>We propose Spatial and Frequency Priors (SFP) for real-world scene recovery.
  arXiv  Detail & Related papers  (2025-12-09T05:24:25Z)
• Spectral Super-Resolution Neural Operator with Atmospheric Radiative Transfer Prior [28.251877082351744]
  Spectral super-resolution (SSR) aims to reconstruct hyperspectral images (HSIs) from multispectral observations.<n>Data-driven methods are widely used, but they often overlook physical principles, leading to unrealistic spectra.<n>We propose the Spectral Super-Resolution Neural Operator (SSRNO), which incorporates atmospheric radiative transfer (ART) prior into the data-driven procedure.
  arXiv  Detail & Related papers  (2025-11-22T02:58:03Z)
• Total Variation Subgradient Guided Image Fusion for Dual-Camera CASSI System [3.414706880536149]
  Spectral imaging technology has long-faced fundamental challenges in balancing spectral, spatial, and temporal resolutions.<n>Traditional model-based methods exhibit limited performance due to reliance on handcrafted inherent image priors.<n>We propose a dual-camera CASSI reconstruction framework that integrates total variation (TV) subgradient theory.
  arXiv  Detail & Related papers  (2025-09-13T16:57:06Z)
• FRN: Fractal-Based Recursive Spectral Reconstruction Network [32.54705293932158]
  spectral reconstruction can significantly reduce the cost of hyperspectral images (HSIs) from RGB images.<n>We propose a Fractal-Based Recursive Spectral Reconstruction Network (FRN) which treats spectral reconstruction as a progressive process.<n> FRN achieves superior reconstruction performance compared to state-of-the-art methods in both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2025-05-21T12:20:59Z)
• Binned Spectral Power Loss for Improved Prediction of Chaotic Systems [0.0]
  We introduce a novel approach to mitigate the spectral bias which we call the Binned Spectral Power ( BSP) Loss.<n>Unlike traditional losses that focus on pointwise misfits, our BSP loss explicitly penalizes deviations in the energy distribution across different scales.<n>Our results demonstrate that the BSP loss significantly improves the stability and spectral accuracy of neural forecasting models.
  arXiv  Detail & Related papers  (2025-02-01T15:58:21Z)
• Self-supervised Deep Hyperspectral Inpainting with the Plug and Play and Deep Image Prior Models [6.8557067473167415]
  Hyperspectral images are typically composed of hundreds of narrow and contiguous spectral bands, each containing information regarding the composition of the imaged scene.<n>These images can be affected by various sources of noise, distortions data, or material loss, which can significantly degrade their quality and usefulness.<n>This paper introduces a converge a guaranteed algorithm, LRS-nt-DIP, which successfully addresses the instability issue of DHP.
  arXiv  Detail & Related papers  (2025-01-14T15:18:28Z)
• ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution [76.7408734079706]
  Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation. We propose ESSAformer, an ESSA attention-embedded Transformer network for single-HSI-SR with an iterative refining structure.
  arXiv  Detail & Related papers  (2023-07-26T07:45:14Z)
• 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)
• Diffusion Probabilistic Model Made Slim [128.2227518929644]
  We introduce a customized design for slim diffusion probabilistic models (DPM) for light-weight image synthesis. We achieve 8-18x computational complexity reduction as compared to the latent diffusion models on a series of conditional and unconditional image generation tasks.
  arXiv  Detail & Related papers  (2022-11-27T16:27:28Z)
• Residual Degradation Learning Unfolding Framework with Mixing Priors across Spectral and Spatial for Compressive Spectral Imaging [29.135848304404533]
  coded aperture snapshot spectral imaging (CASSI) is proposed. core problem of the CASSI system is to recover the reliable and fine underlying 3D spectral cube from the 2D measurement. We propose a Residual Degradation Learning Unfolding Framework (RDLUF) which bridges the gap between the sensing matrix and the degradation process.
  arXiv  Detail & Related papers  (2022-11-13T12:31:49Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• A Fast Alternating Minimization Algorithm for Coded Aperture Snapshot Spectral Imaging Based on Sparsity and Deep Image Priors [8.890754092562918]
  Coded aperture snapshot spectral imaging (CASSI) is a technique used to reconstruct three-dimensional hyperspectral images (HSIs) This paper proposes a fast alternating minimization algorithm based on the sparsity and deep image priors (Fama-P) of natural images.
  arXiv  Detail & Related papers  (2022-06-12T03:29:14Z)
• On Measuring and Controlling the Spectral Bias of the Deep Image Prior [63.88575598930554]
  The deep image prior has demonstrated the remarkable ability that untrained networks can address inverse imaging problems. It requires an oracle to determine when to stop the optimization as the performance degrades after reaching a peak. We study the deep image prior from a spectral bias perspective to address these problems.
  arXiv  Detail & Related papers  (2021-07-02T15:10:42Z)
• Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery [79.69449412334188]
  In this paper, we investigate how to adapt state-of-the-art residual learning based single gray/RGB image super-resolution approaches. We introduce a spatial-spectral prior network (SSPN) to fully exploit the spatial information and the correlation between the spectra of the hyperspectral data. Experimental results on some hyperspectral images demonstrate that the proposed SSPSR method enhances the details of the recovered high-resolution hyperspectral images.
  arXiv  Detail & Related papers  (2020-05-18T14:25:50Z)
• The Power of Triply Complementary Priors for Image Compressive Sensing [89.14144796591685]
  We propose a joint low-rank deep (LRD) image model, which contains a pair of complementaryly trip priors. We then propose a novel hybrid plug-and-play framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-based image CS problem.
  arXiv  Detail & Related papers  (2020-05-16T08:17:44Z)

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.