arXiv:2607. 02693v1 Announce Type: cross Abstract: This study presents a conditional Generative Adversarial Network (cGAN) framework for generating 3D porous media volumes with controlled porosity, trained exclusively on 2D thin section images.
arXiv:2510. 19465v2 Announce Type: replace-cross Abstract: Obtaining truly representative pore-scale images that match bulk formation properties remains a fundamental challenge in subsurface characterization, as natural spatial heterogeneity causes extracted sub-images to deviate significantly from core-measured values.
The paper presents a hybrid generative model that combines denoising diffusion and adversarial training to produce 3D geological microstructures from 2D images. It addresses limitations of previous GAN-based methods like SliceGAN, particularly for heterogeneous materials, by replacing the denoising loss with an adversarial loss to achieve stable training. The resulting model generates microstructures with minimal slice artefacts and accurate phase fractions and structural descriptors.
arXiv:2204. 14224v3 Announce Type: replace-cross Abstract: The automated analysis of heterogeneous natural textures is frequently hindered by physical damage and data loss, presenting a significant challenge to computer vision.
arXiv:2404.17569v4 Announce Type: replace Abstract: This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing methods that synthesize texture maps, we propose to gen...
arXiv:2602. 06989v2 Announce Type: replace-cross Abstract: Carbonate reservoirs offer significant capacity for subsurface carbon storage, oil production, and underground hydrogen storage.
arXiv:2607. 24274v1 Announce Type: cross Abstract: Inverse design of three-dimensional porous media is central to applications in filtration, catalysis, energy storage, fuel cells, thermal management, and biomedical scaffolds, but remains challenging because many distinct pore geometries can share similar porosity or permeability while small structural changes can strongly affect transport behaviour.
arXiv:2602.08727v2 Announce Type: replace-cross Abstract: Undersampled CT volumes minimize acquisition time and radiation exposure but introduce artifacts degrading image quality and diagnostic utili...
arXiv:2606. 13341v1 Announce Type: cross Abstract: We present a Dual-Domain Equivariant Generative Adversarial Network (DDE-GAN) for multimodal CT-PET image synthesis.
The paper introduces an end‑to‑end automated pipeline that generates controllable crack data for deep‑learning inspection. It uses procedurally sampled Bézier‑curve skeletons converted into realistic crack masks via a GAN, and a dual‑ControlNet diffusion model that separates appearance from geometry while enforcing boundary consistency. The method supports both background‑free synthesis and context‑aware inpainting, and shows improved performance over existing augmentation baselines on CRACK500 and CrackTree200 datasets.
The paper introduces ToW3D, a method for precise and consistent control over 3D generative adversarial networks (GANs) using a Tug-of-War approach between shape deformation and appearance consistency. It addresses the challenge that 3D generators often lack generalization, leading to drastic global appearance changes when editing local mesh areas. ToW3D employs a two-step optimization—drag locally and shove globally—along with a structure adaptation module and a semantic preservation module, achieving superior appearance consistency and fidelity compared to prior methods, especially under large deformations.
PoseDreamer is a new pipeline that uses diffusion models to generate large‑scale synthetic datasets for 3D human mesh estimation, providing 3D mesh annotations that remain aligned with the generated images. The system incorporates controllable image generation, Direct Preference Optimization for control alignment, curriculum‑based hard sample mining, and multi‑stage quality filtering to produce over 500,000 high‑quality samples with a 76% improvement in image‑quality metrics over traditional rendering‑based datasets. Models trained on PoseDreamer match or surpass those trained on real‑world or conventional synthetic data, and combining PoseDreamer with synthetic datasets yields better performance than mixing real and synthetic data alone.
The paper introduces 3D Morphological Perturbations, an optimization‑free regularizer for 3D representations such as NeRF and 3D Gaussian Splatting. By treating each Gaussian as a pixel‑like element, the method applies scale, rotation, and pruning perturbations to preserve spatial consistency across views, eliminating the need for per‑scene optimization during dataset curation. Experiments on a lightweight video diffusion sandbox and a 14B‑parameter video model show that the approach improves geometric priors, reduces mean depth error by 12.5% over state‑of‑the‑art 3D artifact refiners, and boosts downstream robotics policy success rates by up to 8.0% on three manipulation tasks.