Hybrid operator learning of wave scattering maps in high-contrast media

• URL: http://arxiv.org/abs/2602.11197v1
• Date: Fri, 30 Jan 2026 23:11:01 GMT
• Title: Hybrid operator learning of wave scattering maps in high-contrast media
• Authors: Advait Balaji, Trevor Teolis, S. David Mis, Jose Antonio Lara Benitez, Chao Wang, Maarten V. de Hoop,
• Abstract summary: We propose a hybrid architecture that decomposes the scattering operator into two separate contributions: a smooth background propagation and a high-contrast scattering correction.<n>The hybrid model achieves substantially improved phase and amplitude accuracy compared to standalone FNOs or transformers.
• Score: 9.371869136168362
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Surrogate modeling of wave propagation and scattering (i.e. the wave speed and source to wave field map) in heterogeneous media has significant potential in applications such as seismic imaging and inversion. High-contrast settings, such as subsurface models with salt bodies, exhibit strong scattering and phase sensitivity that challenge existing neural operators. We propose a hybrid architecture that decomposes the scattering operator into two separate contributions: a smooth background propagation and a high-contrast scattering correction. The smooth component is learned with a Fourier Neural Operator (FNO), which produces globally coupled feature tokens encoding background wave propagation; these tokens are then passed to a vision transformer, where attention is used to model the high-contrast scattering correction dominated by strong, spatial interactions. Evaluated on high-frequency Helmholtz problems with strong contrasts, the hybrid model achieves substantially improved phase and amplitude accuracy compared to standalone FNOs or transformers, with favorable accuracy-parameter scaling.

Related papers

• Wavefront-Constrained Passive Obscured Object Detection [18.56759054781774]
  Accurately localizing and segmenting obscured objects from faint light patterns beyond the field of view is highly challenging.<n>Most existing methods, based on real-valued modeling or local convolutional operations, are inadequate for capturing the underlying physics of coherent light propagation.<n>We propose a physics-driven Wavefront Propagating Compensation Network (WavePCNet) to simulate wavefront propagation and enhance the perception of obscured objects.
  arXiv  Detail & Related papers  (2025-11-26T02:46:15Z)
• Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers [55.15722080205737]
  Edit2Perceive is a unified diffusion framework that adapts editing models for depth, normal, and matting.<n>Our single-step deterministic inference yields up to faster runtime while training on relatively small datasets.
  arXiv  Detail & Related papers  (2025-11-24T01:13:51Z)
• TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization [11.970228442183476]
  We propose a diffusion-based TIR image denoising framework.<n>Our method fine-tunes the model via a novel loss function combining latent-space and discrete wavelet transform (DWT) / dual-tree complex wavelet transform (DTCWT) losses.<n> Experiments on benchmark datasets demonstrate superior performance of our approach compared to state-of-the-art denoising methods.
  arXiv  Detail & Related papers  (2025-07-30T06:27:32Z)
• Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis [56.311477476580926]
  We present Latent Wavelet Diffusion (LWD), a lightweight training framework that significantly improves detail and texture fidelity in ultra-high-resolution (2K-4K) image synthesis.<n>LWD introduces a novel, frequency-aware masking strategy derived from wavelet energy maps, which dynamically focuses the training process on detail-rich regions of the latent space.
  arXiv  Detail & Related papers  (2025-05-31T07:28:32Z)
• PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classification [49.37555541088792]
  Phase-Amplitude Decoupling (PAD) is a frequency-aware framework that separates phase (modality-shared) and amplitude (modality-complementary) components.<n>This work establishes a new paradigm for physics-aware multi-modal fusion in remote sensing.
  arXiv  Detail & Related papers  (2025-04-27T07:21:42Z)
• A Hybrid Wavelet-Fourier Method for Next-Generation Conditional Diffusion Models [0.0]
  We present a novel generative modeling framework,Wavelet-Fourier-Diffusion, which adapts the diffusion paradigm to hybrid frequency representations.<n>We show how the hybrid frequency-based representation improves control over global coherence and fine texture synthesis.
  arXiv  Detail & Related papers  (2025-04-04T17:11:04Z)
• Haar Nuclear Norms with Applications to Remote Sensing Imagery Restoration [53.68392692185276]
  This paper proposes a novel low-rank regularization term, named the Haar nuclear norm (HNN), for efficient and effective remote sensing image restoration.<n>It leverages the low-rank properties of wavelet coefficients derived from the 2-D frontal slice-wise Haar discrete wavelet transform.<n> Experimental evaluations conducted on hyperspectral image inpainting, multi-temporal image cloud removal, and hyperspectral image denoising have revealed the HNN's potential.
  arXiv  Detail & Related papers  (2024-07-11T13:46:47Z)
• Shaping entangled photons through thick scattering media using an advanced wave beacon [0.0]
  Entangled photons propagate through a complex medium such as a biological tissue or a turbulent atmosphere. Using wavefront shaping to compensate for the scattering and retrieve the two-photon correlations is challenging due to the low signal-to-noise ratio. We propose and demonstrate a new feedback mechanism that is inspired by Klyshko's advanced wave picture.
  arXiv  Detail & Related papers  (2024-03-27T07:56:13Z)
• Hybrid Convolutional and Attention Network for Hyperspectral Image Denoising [54.110544509099526]
  Hyperspectral image (HSI) denoising is critical for the effective analysis and interpretation of hyperspectral data. We propose a hybrid convolution and attention network (HCANet) to enhance HSI denoising. Experimental results on mainstream HSI datasets demonstrate the rationality and effectiveness of the proposed HCANet.
  arXiv  Detail & Related papers  (2024-03-15T07:18:43Z)
• Stage-by-stage Wavelet Optimization Refinement Diffusion Model for Sparse-View CT Reconstruction [14.037398189132468]
  We present an innovative approach named the Stage-by-stage Wavelet Optimization Refinement Diffusion (SWORD) model for sparse-view CT reconstruction. Specifically, we establish a unified mathematical model integrating low-frequency and high-frequency generative models, achieving the solution with optimization procedure. Our method rooted in established optimization theory, comprising three distinct stages, including low-frequency generation, high-frequency refinement and domain transform.
  arXiv  Detail & Related papers  (2023-08-30T10:48:53Z)
• Hyper-entanglement between pulse modes and frequency bins [101.18253437732933]
  Hyper-entanglement between two or more photonic degrees of freedom (DOF) can enhance and enable new quantum protocols. We demonstrate the generation of photon pairs hyper-entangled between pulse modes and frequency bins.
  arXiv  Detail & Related papers  (2023-04-24T15:43:08Z)

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.