Towards Photonic Band Diagram Generation with Transformer-Latent Diffusion Models

• URL: http://arxiv.org/abs/2510.01749v1
• Date: Thu, 02 Oct 2025 07:35:28 GMT
• Title: Towards Photonic Band Diagram Generation with Transformer-Latent Diffusion Models
• Authors: Valentin Delchevalerie, Nicolas Roy, Arnaud Bougaham, Alexandre Mayer, Benoît Frénay, Michaël Lobet,
• Abstract summary: Photonic band diagrams (BDs) are a key tool to investigate light propagation into inhomogeneous structured materials.<n>We introduce the first approach for BD generation based on diffusion models.<n>Our method couples a transformer encoder, which extracts contextual embeddings from the input structure, with a latent diffusion model to generate the corresponding BD.
• Score: 36.68704595055831
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Photonic crystals enable fine control over light propagation at the nanoscale, and thus play a central role in the development of photonic and quantum technologies. Photonic band diagrams (BDs) are a key tool to investigate light propagation into such inhomogeneous structured materials. However, computing BDs requires solving Maxwell's equations across many configurations, making it numerically expensive, especially when embedded in optimization loops for inverse design techniques, for example. To address this challenge, we introduce the first approach for BD generation based on diffusion models, with the capacity to later generalize and scale to arbitrary three dimensional structures. Our method couples a transformer encoder, which extracts contextual embeddings from the input structure, with a latent diffusion model to generate the corresponding BD. In addition, we provide insights into why transformers and diffusion models are well suited to capture the complex interference and scattering phenomena inherent to photonics, paving the way for new surrogate modeling strategies in this domain.

Related papers

• 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)
• Physics-guided and fabrication-aware inverse design of photonic devices using diffusion models [43.51581973358462]
  We present AdjointDiffusion, a physics-guided framework that integrates adjoint gradient sensitivity into the sampling process of diffusion models.<n>Our method consistently outperforms state-of-the-art nonlinear gradient approaches in both efficiency and manufacturability.
  arXiv  Detail & Related papers  (2025-04-23T19:54:33Z)
• 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)
• Effective Diffusion Transformer Architecture for Image Super-Resolution [63.254644431016345]
  We design an effective diffusion transformer for image super-resolution (DiT-SR) In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks. We analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module.
  arXiv  Detail & Related papers  (2024-09-29T07:14:16Z)
• Transformers from Diffusion: A Unified Framework for Neural Message Passing [79.9193447649011]
  Message passing neural networks (MPNNs) have become a de facto class of model solutions.<n>We propose an energy-constrained diffusion model, which integrates the inductive bias of diffusion with layer-wise constraints of energy.<n>Building on these insights, we devise a new class of message passing models, dubbed Transformers (DIFFormer), whose global attention layers are derived from the principled energy-constrained diffusion framework.
  arXiv  Detail & Related papers  (2024-09-13T17:54:41Z)
• Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesis [10.428185253933004]
  We replace Gaussian decoders with a non-isotropic diffusion model at the decoder side. Our framework is equipped with a novel entropy model that accurately models probability distribution latent representation. Our experiments demonstrate that our framework yields better perceptual quality compared to cutting-edge generative entropy-based codecs.
  arXiv  Detail & Related papers  (2024-03-24T18:33:16Z)
• Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency [7.671153315762146]
  Training diffusion models in the pixel space are both data-intensive and computationally demanding. Latent diffusion models, which operate in a much lower-dimensional space, offer a solution to these challenges. We propose textitReSample, an algorithm that can solve general inverse problems with pre-trained latent diffusion models.
  arXiv  Detail & Related papers  (2023-07-16T18:42:01Z)
• Controlling Text-to-Image Diffusion by Orthogonal Finetuning [74.21549380288631]
  We introduce a principled finetuning method -- Orthogonal Finetuning (OFT) for adapting text-to-image diffusion models to downstream tasks. Unlike existing methods, OFT can provably preserve hyperspherical energy which characterizes the pairwise neuron relationship on the unit hypersphere. We empirically show that our OFT framework outperforms existing methods in generation quality and convergence speed.
  arXiv  Detail & Related papers  (2023-06-12T17:59:23Z)
• Dimensionality-Varying Diffusion Process [52.52681373641533]
  Diffusion models learn to reverse a signal destruction process to generate new data. We make a theoretical generalization of the forward diffusion process via signal decomposition. We show that our strategy facilitates high-resolution image synthesis and improves FID of diffusion model trained on FFHQ at $1024times1024$ resolution from 52.40 to 10.46.
  arXiv  Detail & Related papers  (2022-11-29T09:05:55Z)

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.