Urban Neural Surface Reconstruction from Constrained Sparse Aerial Imagery with 3D SAR Fusion

2026-01-29

AI Summary

This work addresses the challenges of neural surface reconstruction in urban environments from sparse-view aerial imagery, where geometric ambiguity and instability commonly degrade performance. To mitigate these issues, the authors propose a novel signed distance function (SDF)-based neural reconstruction framework that uniquely integrates 3D synthetic aperture radar (SAR) point clouds with sparse aerial images. By incorporating SAR-derived geometric priors, the method enables structure-aware ray selection and adaptive sampling during reconstruction. The study also introduces the first registered multimodal benchmark dataset for urban reconstruction, facilitating comprehensive evaluation under highly sparse and oblique viewing conditions. Experimental results demonstrate that the proposed approach significantly improves reconstruction accuracy, completeness, and robustness compared to existing single-modality methods.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Neural surface reconstruction (NSR) has recently shown strong potential for urban 3D reconstruction from multi-view aerial imagery. However, existing NSR methods often suffer from geometric ambiguity and instability, particularly under sparse-view conditions. This issue is critical in large-scale urban remote sensing, where aerial image acquisition is limited by flight paths, terrain, and cost. To address this challenge, we present the first urban NSR framework that fuses 3D synthetic aperture radar (SAR) point clouds with aerial imagery for high-fidelity reconstruction under constrained, sparse-view settings. 3D SAR can efficiently capture large-scale geometry even from a single side-looking flight path, providing robust priors that complement photometric cues from images. Our framework integrates radar-derived spatial constraints into an SDF-based NSR backbone, guiding structure-aware ray selection and adaptive sampling for stable and efficient optimization. We also construct the first benchmark dataset with co-registered 3D SAR point clouds and aerial imagery, facilitating systematic evaluation of cross-modal 3D reconstruction. Extensive experiments show that incorporating 3D SAR markedly enhances reconstruction accuracy, completeness, and robustness compared with single-modality baselines under highly sparse and oblique-view conditions, highlighting a viable route toward scalable high-fidelity urban reconstruction with advanced airborne and spaceborne optical-SAR sensing.

Problem

• Neural Surface Reconstruction
• Sparse-view Reconstruction
• Urban 3D Reconstruction
• Geometric Ambiguity
• 3D SAR Fusion

Innovation

• Neural Surface Reconstruction
• 3D SAR Fusion
• Sparse-View Urban Reconstruction
• Cross-Modal 3D Reconstruction
• SDF-based Optimization