Sat-mesh: Learning neural implicit surfaces for multi-view satellite reconstruction

Y Qu, F Deng - Remote Sensing, 2023 - mdpi.com
Automatic reconstruction of surfaces from satellite imagery is a hot topic in computer vision
and photogrammetry. State-of-the-art reconstruction methods typically produce 2.5 D …

Accelerating NeRF with the Visual Hull

R Marí - Image Processing On Line, 2024 - ipol.im
Neural rendering methods for learning the appearance and geometry of 3D scenes have
gained tremendous popularity since 2020. In this field, NeRF or Neural Radiance Fields is …

[HTML][HTML] Constraining the Geometry of NeRFs for Accurate DSM Generation from Multi-View Satellite Images

Q Wan, Y Guan, Q Zhao, X Wen, J She - ISPRS International Journal of …, 2024 - mdpi.com
Neural Radiance Fields (NeRFs) are an emerging approach to 3D reconstruction that use
neural networks to reconstruct scenes. However, its applications for multi-view satellite …

Radar Fields: An Extension of Radiance Fields to SAR

T Ehret, R Marí, D Derksen… - Proceedings of the …, 2024 - openaccess.thecvf.com
Radiance fields have been a major breakthrough in the field of inverse rendering novel view
synthesis and 3D modeling of complex scenes from multi-view image collections. Since their …

SUNDIAL: 3D Satellite Understanding through Direct Ambient and Complex Lighting Decomposition

N Behari, A Dave, K Tiwary… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract 3D modeling from satellite imagery is essential in areas of environmental science
urban planning agriculture and disaster response. However traditional 3D modeling …

SingleRecon: Reconstructing Building 3D models of LoD1 from A Single Off-Nadir Remote Sensing Image

R Shao, JJ Wu, J Li, S Peng, H Chen… - IEEE Journal of Selected …, 2024 - ieeexplore.ieee.org
3-D building models are one of the most intuitive and widely used forms for understanding
urban buildings. Generating 3-D building models based on a single off-nadir satellite image …

NeRF-Based Large-Scale Urban True Digital Orthophoto Map Generation Method

J Wei, G Zhu, X Chen - IEEE Journal of Selected Topics in …, 2024 - ieeexplore.ieee.org
In urban scenes, there are man-made ground objects with complex structures and significant
height differences, which leads to challenges in generating large-scale true digital …

FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitions

M Sprintson, R Chellappa, C Peng - arXiv preprint arXiv:2409.15132, 2024 - arxiv.org
We introduce FusionRF, a novel neural rendering terrain reconstruction method from
optically unprocessed satellite imagery. While previous methods depend on external …

FVMD-ISRe: 3D Reconstruction from Few-View Multi-Date Satellite Images Based on the Implicit Surface Representation of Neural Radiance Fields

C Zhang, Y Yan, C Zhao, N Su… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Three-dimensional reconstruction utilizing few-view satellite images can effectively reduce
the cost of resources. However, methods that rely on dense stereo matching suffer severe …

Generative Artificial Intelligence Meets Synthetic Aperture Radar: A survey

Z Huang, X Zhang, Z Tang, F Xu… - IEEE Geoscience and …, 2024 - ieeexplore.ieee.org
SAR images possess unique attributes that present challenges for both human observers
and vision AI models to interpret, owing to their electromagnetic characteristics. The …