GeoDiff-SAR: A Geometric Prior Guided Diffusion Model for SAR Image Generation

• URL: http://arxiv.org/abs/2601.03499v1
• Date: Wed, 07 Jan 2026 01:27:20 GMT
• Title: GeoDiff-SAR: A Geometric Prior Guided Diffusion Model for SAR Image Generation
• Authors: Fan Zhang, Xuanting Wu, Fei Ma, Qiang Yin, Yuxin Hu,
• Abstract summary: Existing generative methods primarily operate within the image domain, neglecting explicit geometric information.<n>We propose GeoDiff-SAR, a geometric prior guided diffusion model for high-fidelity SAR image generation.<n>Results demonstrate that data generated by GeoDiff-SAR exhibits high fidelity and effectively enhances the accuracy of downstream classification tasks.
• Score: 8.561613404715237
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Synthetic Aperture Radar (SAR) imaging results are highly sensitive to observation geometries and the geometric parameters of targets. However, existing generative methods primarily operate within the image domain, neglecting explicit geometric information. This limitation often leads to unsatisfactory generation quality and the inability to precisely control critical parameters such as azimuth angles. To address these challenges, we propose GeoDiff-SAR, a geometric prior guided diffusion model for high-fidelity SAR image generation. Specifically, GeoDiff-SAR first efficiently simulates the geometric structures and scattering relationships inherent in real SAR imaging by calculating SAR point clouds at specific azimuths, which serves as a robust physical guidance. Secondly, to effectively fuse multi-modal information, we employ a feature fusion gating network based on Feature-wise Linear Modulation (FiLM) to dynamically regulate the weight distribution of 3D physical information, image control parameters, and textual description parameters. Thirdly, we utilize the Low-Rank Adaptation (LoRA) architecture to perform lightweight fine-tuning on the advanced Stable Diffusion 3.5 (SD3.5) model, enabling it to rapidly adapt to the distribution characteristics of the SAR domain. To validate the effectiveness of GeoDiff-SAR, extensive comparative experiments were conducted on real-world SAR datasets. The results demonstrate that data generated by GeoDiff-SAR exhibits high fidelity and effectively enhances the accuracy of downstream classification tasks. In particular, it significantly improves recognition performance across different azimuth angles, thereby underscoring the superiority of physics-guided generation.

Related papers

• ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting [63.138778159026934]
  We propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO.<n> ERGO dynamically estimates the view-specific excess risk and adaptively adjust loss weights during optimization.<n>Experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-10T20:44:43Z)
• Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process [93.00033672476206]
  GeoDiff-LF is a novel diffusion-based framework built upon SD-Turbo to enhance underwater 4-D LF imaging.<n>By integrating diffusion priors and LF geometry, GeoDiff-LF effectively mitigates color distortion in underwater scenes.
  arXiv  Detail & Related papers  (2026-01-29T02:27:22Z)
• Robust Mesh Saliency GT Acquisition in VR via View Cone Sampling and Geometric Smoothing [59.12032628787018]
  3D mesh saliency ground truth is essential for human-centric visual modeling in virtual reality (VR)<n>Current VR eye-tracking pipelines rely on single ray sampling and Euclidean smoothing, triggering texture attention and signal leakage across gaps.<n>This paper proposes a robust framework to address these limitations.
  arXiv  Detail & Related papers  (2026-01-06T05:20:12Z)
• GDROS: A Geometry-Guided Dense Registration Framework for Optical-SAR Images under Large Geometric Transformations [24.22541638346487]
  We propose GDROS, a geometry-guided dense registration framework leveraging global cross-modal image interactions.<n>First, we extract cross-modal deep features from optical and SAR images through a CNN-Transformer hybrid feature extraction module.<n>We then implement a least squares regression (LSR) module to geometrically constrain the predicted dense optical flow field.
  arXiv  Detail & Related papers  (2025-11-01T15:40:34Z)
• Geometry-aware Active Learning of Spatiotemporal Dynamic Systems [4.251030047034566]
  This paper proposes a geometry-aware active learning framework for modeling dynamic systems.<n>We develop an adaptive active learning strategy to strategically identify spatial locations for data collection and further maximize the prediction accuracy.
  arXiv  Detail & Related papers  (2025-04-26T19:56:38Z)
• $\mathbfΦ$-GAN: Physics-Inspired GAN for Generating SAR Images Under Limited Data [45.83064997810622]
  We propose a physics-inspired regularization method dubbed $Phi$-GAN for synthetic aperture radar (SAR) images.<n>The PSC model approximates SAR targets using physical parameters, ensuring that $Phi$-GAN generates SAR images consistent with real physical properties.<n>We evaluate $Phi$-GAN across several conditional GAN (cGAN) models, demonstrating state-of-the-art performance in data-scarce scenarios.
  arXiv  Detail & Related papers  (2025-03-04T03:32:11Z)
• RSGaussian:3D Gaussian Splatting with LiDAR for Aerial Remote Sensing Novel View Synthesis [6.900071309404811]
  RSGaussian is an innovative novel view synthesis (NVS) method for aerial remote sensing scenes.<n>It incorporates LiDAR point cloud as constraints into the 3D Gaussian Splatting method, which ensures that Gaussians grow and split along geometric benchmarks.<n>The approach also introduces coordinate transformations with distortion parameters for camera models to achieve pixel-level alignment between LiDAR point clouds and 2D images.
  arXiv  Detail & Related papers  (2024-12-24T12:08:50Z)
• 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction [50.07071392673984]
  Existing methods learn 3D rotations parametrized in the spatial domain using angles or quaternions. We propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression. Our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+.
  arXiv  Detail & Related papers  (2024-11-01T12:50:38Z)
• GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering [69.67264955234494]
  GeoSplatting is a novel approach that augments 3DGS with explicit geometry guidance for precise light transport modeling.<n>By differentiably constructing a surface-grounded 3DGS from an optimizable mesh, our approach leverages well-defined mesh normals and the opaque mesh surface.<n>This enhancement ensures precise material decomposition while preserving the efficiency and high-quality rendering capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-31T17:57:07Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• SAR-AE-SFP: SAR Imagery Adversarial Example in Real Physics domain with Target Scattering Feature Parameters [2.3930545422544856]
  Current adversarial example generation methods for SAR imagery operate in the 2D digital domain, known as image adversarial examples. This paper proposes SAR-AE-SFP-Attack, a method to generate real physics adversarial examples by altering the scattering feature parameters of target objects. Experimental results show that SAR-AE-SFP Attack significantly improves attack efficiency on CNN-based models and Transformer-based models.
  arXiv  Detail & Related papers  (2024-03-02T13:52:28Z)
• Learning Surface Scattering Parameters From SAR Images Using Differentiable Ray Tracing [8.19502673278742]
  This paper proposes a surface microwave rendering model that comprehensively considers both Specular and Diffuse contributions. A differentiable ray tracing (DRT) engine based on SAR images was constructed for CSVBSDF surface scattering parameter learning. The effectiveness of this approach has been validated through simulations and comparisons with real SAR images.
  arXiv  Detail & Related papers  (2024-01-02T12:09:06Z)

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.