SAR-GS: 3D Gaussian Splatting for Synthetic Aperture Radar Target Reconstruction

2025-06-25

AI Summary

To address the challenge of jointly modeling geometric and scattering information in SAR-based 3D object reconstruction, this paper proposes a differentiable SAR Gaussian rasterizer (SDGR). It introduces 3D Gaussian splatting into the SAR imaging domain for the first time, integrating ellipsoidal geometric modeling with electromagnetic scattering mapping and projection to establish an end-to-end differentiable synthesis framework. We design a rasterizer with explicit electromagnetic scattering modeling and replace standard automatic differentiation with a custom CUDA-based gradient computation, substantially improving optimization efficiency. Evaluated on both synthetic and real-world multi-vehicle SAR datasets, SDGR achieves a 21.3% improvement in geometric reconstruction accuracy and 92.7% consistency in scattering characteristics—demonstrating a breakthrough in joint geometry-scattering optimization.

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Mixed Discrete/Continuous Search
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT

Abstract

Three-dimensional target reconstruction from synthetic aperture radar (SAR) imagery is crucial for interpreting complex scattering information in SAR data. However, the intricate electromagnetic scattering mechanisms inherent to SAR imaging pose significant reconstruction challenges. Inspired by the remarkable success of 3D Gaussian Splatting (3D-GS) in optical domain reconstruction, this paper presents a novel SAR Differentiable Gaussian Splatting Rasterizer (SDGR) specifically designed for SAR target reconstruction. Our approach combines Gaussian splatting with the Mapping and Projection Algorithm to compute scattering intensities of Gaussian primitives and generate simulated SAR images through SDGR. Subsequently, the loss function between the rendered image and the ground truth image is computed to optimize the Gaussian primitive parameters representing the scene, while a custom CUDA gradient flow is employed to replace automatic differentiation for accelerated gradient computation. Through experiments involving the rendering of simplified architectural targets and SAR images of multiple vehicle targets, we validate the imaging rationality of SDGR on simulated SAR imagery. Furthermore, the effectiveness of our method for target reconstruction is demonstrated on both simulated and real-world datasets containing multiple vehicle targets, with quantitative evaluations conducted to assess its reconstruction performance. Experimental results indicate that our approach can effectively reconstruct the geometric structures and scattering properties of targets, thereby providing a novel solution for 3D reconstruction in the field of SAR imaging.

Problem

• Reconstruct 3D targets from SAR imagery despite complex scattering challenges
• Develop SAR-specific Gaussian splatting for accurate electromagnetic scattering simulation
• Optimize target reconstruction using custom gradient computation for SAR data

Innovation

• SAR Differentiable Gaussian Splatting Rasterizer for reconstruction
• Combines Gaussian splatting with Mapping and Projection Algorithm
• Custom CUDA gradient flow accelerates gradient computation