MicroLad: 2D-to-3D Microstructure Reconstruction and Generation via Latent Diffusion and Score Distillation

• URL: http://arxiv.org/abs/2508.20138v3
• Date: Wed, 05 Nov 2025 23:19:33 GMT
• Title: MicroLad: 2D-to-3D Microstructure Reconstruction and Generation via Latent Diffusion and Score Distillation
• Authors: Kang-Hyun Lee, Faez Ahmed,
• Abstract summary: MicroLad is a latent diffusion framework specifically designed for reconstructing 3D microstructures from 2D data.<n>It reliably generates stable and coherent 3D volumes that remain statistically consistent with the original data.
• Score: 5.6883658862830115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A major obstacle to establishing reliable structure-property (SP) linkages in materials engineering is the scarcity of diverse 3D microstructure datasets. Limited dataset availability and insufficient control over the analysis and design space restrict the variety of achievable microstructure morphologies, hindering progress in solving the inverse (property-to-structure) design problem. To address these challenges, we introduce MicroLad, a latent diffusion framework specifically designed for reconstructing 3D microstructures from 2D data. Trained on 2D images and employing multi-plane denoising diffusion sampling in the latent space, the framework reliably generates stable and coherent 3D volumes that remain statistically consistent with the original data. While this reconstruction capability enables dimensionality expansion (2D-to-3D) for generating statistically equivalent 3D samples from 2D data, effective exploration of microstructure design requires methods to guide the generation process toward specific objectives. To achieve this, MicroLad integrates score distillation sampling (SDS), which combines a differentiable score loss with microstructural descriptor-matching and property-alignment terms. This approach updates encoded 2D slices of the 3D volume in the latent space, enabling robust inverse-controlled 2D-to-3D microstructure generation. Consequently, the method facilitates exploration of an expanded 3D microstructure analysis and design space in terms of both microstructural descriptors and material properties.

Related papers

• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• Unified Few-shot Crack Segmentation and its Precise 3D Automatic Measurement in Concrete Structures [2.178830801484721]
  This study introduces a framework for two-dimensional (2D) crack detection, three-dimensional (3D) reconstruction, and 3D automatic crack measurement.<n>We developed a crack segmentation method with strong generalization across unfamiliar scenarios, enabling the generation of precise 2D crack masks.<n>By leveraging both image- and LiDAR-SLAM, we developed a multi-frame and multi-modal fusion framework that produces dense, colorized point clouds.
  arXiv  Detail & Related papers  (2025-01-15T23:36:05Z)
• T-3DGS: Removing Transient Objects for 3D Scene Reconstruction [83.05271859398779]
  Transient objects in video sequences can significantly degrade the quality of 3D scene reconstructions.<n>We propose T-3DGS, a novel framework that robustly filters out transient distractors during 3D reconstruction using Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-11-29T07:45:24Z)
• Towards Unified 3D Object Detection via Algorithm and Data Unification [70.27631528933482]
  We build the first unified multi-modal 3D object detection benchmark MM- Omni3D and extend the aforementioned monocular detector to its multi-modal version. We name the designed monocular and multi-modal detectors as UniMODE and MM-UniMODE, respectively.
  arXiv  Detail & Related papers  (2024-02-28T18:59:31Z)
• A Generative Machine Learning Model for Material Microstructure 3D Reconstruction and Performance Evaluation [4.169915659794567]
  The dimensional extension from 2D to 3D is viewed as a highly challenging inverse problem from the current technological perspective. A novel generative model that integrates the multiscale properties of U-net with and the generative capabilities of GAN has been proposed. The model's accuracy is further improved by combining the image regularization loss with the Wasserstein distance loss.
  arXiv  Detail & Related papers  (2024-02-24T13:42:34Z)
• Denoising diffusion-based synthetic generation of three-dimensional (3D) anisotropic microstructures from two-dimensional (2D) micrographs [0.0]
  We present a framework for reconstruction of anisotropic microstructures based on conditional diffusion-based generative models (DGMs) The proposed framework involves spatial connection of multiple 2D conditional DGMs, each trained to generate 2D microstructure samples for three different planes. The results demonstrate that the framework is capable of reproducing not only the statistical distribution of material phases but also the material properties in 3D space.
  arXiv  Detail & Related papers  (2023-12-13T01:36:37Z)
• StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D [88.66678730537777]
  We present StableDreamer, a methodology incorporating three advances. First, we formalize the equivalence of the SDS generative prior and a simple supervised L2 reconstruction loss. Second, our analysis shows that while image-space diffusion contributes to geometric precision, latent-space diffusion is crucial for vivid color rendition.
  arXiv  Detail & Related papers  (2023-12-02T02:27:58Z)
• Multi-plane denoising diffusion-based dimensionality expansion for 2D-to-3D reconstruction of microstructures with harmonized sampling [0.0]
  This study proposes a novel framework for 2D-to-3D reconstruction of microstructures called Micro3Diff. Specifically, this approach solely requires pre-trained DGMs for the generation of 2D samples. A harmonized sampling process is developed to address possible deviations from the reverse Markov chain of DGMs.
  arXiv  Detail & Related papers  (2023-08-27T07:57:25Z)
• DA-VEGAN: Differentiably Augmenting VAE-GAN for microstructure reconstruction from extremely small data sets [110.60233593474796]
  DA-VEGAN is a model with two central innovations. A $beta$-variational autoencoder is incorporated into a hybrid GAN architecture. A custom differentiable data augmentation scheme is developed specifically for this architecture.
  arXiv  Detail & Related papers  (2023-02-17T08:49:09Z)
• MicroLib: A library of 3D microstructures generated from 2D micrographs using SliceGAN [0.0]
  3D microstructural datasets are commonly used to define the geometrical domains used in finite element modelling. Machine learning method, SliceGAN, was developed to statistically generate 3D microstructural datasets of arbitrary size. We present the results from applying SliceGAN to 87 different microstructures, ranging from biological materials to high-strength steels.
  arXiv  Detail & Related papers  (2022-10-12T19:13:28Z)
• 3D Reconstruction of Curvilinear Structures with Stereo Matching DeepConvolutional Neural Networks [52.710012864395246]
  We propose a fully automated pipeline for both detection and matching of curvilinear structures in stereo pairs. We mainly focus on 3D reconstruction of dislocations from stereo pairs of TEM images.
  arXiv  Detail & Related papers  (2021-10-14T23:05:47Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)

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.