WaveFreqAnchor: Wave-Structural Anchoring and Frequency Correction Diffusion for Training-Free Face Restoration

• URL: http://arxiv.org/abs/2608.06717v1
• Date: Fri, 07 Aug 2026 02:23:25 GMT
• Title: WaveFreqAnchor: Wave-Structural Anchoring and Frequency Correction Diffusion for Training-Free Face Restoration
• Abstract summary: WaveFreqAnchor is a training-free framework based on Wave- Structural Anchoring and Frequency Correction Diffusion.<n>MWFI aligns the predicted low-frequency subband with the observation by replacing its phase, correcting inconsistencies accumulated during reverse diffusion.<n>Subband High-Frequency Enhancement (SHE) performs bounded, spatially masked refinement on the predicted high-frequency subbands to recover fine facial details.
• Score: 22.463138159431196
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based face restoration that adjusts the sampling trajectory of pre-trained diffusion models has achieved remarkable progress. However, existing approaches provide insufficient constraints during reverse diffusion, causing identity-related structural drift and degraded fidelity under severe degradations. To address this, we propose WaveFreqAnchor, a training-free framework based on Wave-Structural Anchoring and Frequency Correction Diffusion. Specifically, Anchor-Space Wave-Structural Guidance (ASWG) constrains facial structures through anisotropic wave-response consistency, while Multi-scale Wavelet-Fourier Injection (MWFI) aligns the predicted low-frequency subband with the observation by replacing its phase, correcting inconsistencies accumulated during reverse diffusion. For real-world scenes, we further introduce Subband High-Frequency Enhancement (SHE), which performs bounded, spatially masked refinement on the predicted high-frequency subbands to recover fine facial details under unknown compound degradations. Together, these designs effectively preserve facial identity while restoring sharp and realistic facial details. Extensive experiments show that our method consistently outperforms existing methods, achieving high-quality and high-fidelity face restoration.

Related papers

• Physical-State-Guided Diffusion Sampling for Full-Waveform Inversion [3.497341516063219]
  We propose Physical-State-Guided Diffusion Sampling (PSG)<n>PSG couples a persistent physical velocity to the diffusion prior through a Gaussian bridge.<n>On four OpenFWI families, PSG's terminal denoised estimates outperform classical and diffusion-based baselines.
  arXiv  Detail & Related papers  (2026-09-11T14:25:42Z)
• HNDiff: Haze-Noise Diffusion for Image Dehazing [52.34718859688771]
  Haze-Noise Diffusion (HNDiff) is a novel diffusion framework that embeds the atmospheric scattering model as an inductive bias.<n>In its forward process, we introduce joint haze-noise diffusion with a haze-aware noise scheduler, which progressively adds both haze and noise to an image.<n>In the reverse process, we derive a physically consistent dehazing-denoising process that simultaneously removes haze and noise to restore a clean image.
  arXiv  Detail & Related papers  (2026-08-11T14:47:38Z)
• 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)
• Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting [21.300422393514804]
  We propose a deterministic framework that reformulates nowcasting as progressive frequency-decoupled refinement.<n>SDIR first extracts a stable low-frequency synoptic skeleton, then iteratively refines high-frequency textures under physical constraints.<n> Experiments on three benchmarks show SDIR significantly outperforms SOTA methods in spatial accuracy.
  arXiv  Detail & Related papers  (2026-06-01T07:34:30Z)
• AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priors [10.352581041881864]
  This paper introduces AnyBand-Diff, a spectral-prior-guided diffusion framework tailored for robust spectral reconstruction.<n>To ensure radiometric fidelity, a Physics-Guided Sampling mechanism is proposed.<n>Experiments confirm the effectiveness of AnyBand-Diff in generating reliable imagery.
  arXiv  Detail & Related papers  (2026-05-14T04:04:34Z)
• Signal-Aware Conditional Diffusion Surrogates for Transonic Wing Pressure Prediction [0.0]
  This work presents a conditional denoising diffusion probabilistic model for predicting surface pressure on the NASA Common Research Model wing.<n>A signal-aware training objective is derived by propagating a reconstruction loss through the diffusion process.<n>Relative to the considered deterministic baselines, the proposed formulation reduces mean absolute error and improves the reconstruction of suction peaks, shock structures, and control surface discontinuities.
  arXiv  Detail & Related papers  (2026-04-13T10:18:07Z)
• 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)
• Diffusion prior as a direct regularization term for FWI [0.0]
  We propose a score-based generative diffusion prior into Full Waveform Inversion (FWI)<n>Unlike traditional diffusion approaches, our method avoids the reverse diffusion sampling and needs fewer iterations.<n>The proposed method offers enhanced fidelity and robustness compared to conventional and GAN-based FWI approaches.
  arXiv  Detail & Related papers  (2025-06-11T19:43:23Z)
• WaveFace: Authentic Face Restoration with Efficient Frequency Recovery [74.73492472409447]
  diffusion models are criticized for two problems: 1) slow training and inference speed, and 2) failure in preserving identity and recovering fine-grained facial details. We propose WaveFace to solve the problems in the frequency domain, where low- and high-frequency components decomposed by wavelet transformation are considered individually. We show that WaveFace outperforms state-of-the-art methods in authenticity, especially in terms of identity preservation.
  arXiv  Detail & Related papers  (2024-03-19T14:27:24Z)
• 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)
• DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration [103.79030498369319]
  Self-supervised diffusion model for hyperspectral image restoration is proposed. textttDDS2M enjoys stronger ability to generalization compared to existing diffusion-based methods. Experiments on HSI denoising, noisy HSI completion and super-resolution on a variety of HSIs demonstrate textttDDS2M's superiority over the existing task-specific state-of-the-arts.
  arXiv  Detail & Related papers  (2023-03-12T14:57:04Z)

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.