SAT-NGP : Unleashing Neural Graphics Primitives for Fast Relightable Transient-Free 3D Reconstruction From Satellite Imagery
Authors:
- 7 July 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8749-8753
Abstract
Current stereo-vision pipelines produce high accuracy 3D reconstruction when using multiple pairs or triplets of satellite images. However, these pipelines are sensitive to the changes between images that can occur as a result of multidate acquisitions. Such variations are mainly due to variable shadows, reflexions and transient objects (cars, vegetation). To take such changes into account, Neural Radiance Fields (NeRF) have recently been applied to multi-date satellite imagery. However, Neural methods are very compute-intensive, taking dozens of hours to learn, compared with minutes for standard stereo-vision pipelines. Following the ideas of Instant Neural Graphics Primitives we propose to use an efficient sampling strategy and multi-resolution hash encoding to accelerate the learning. Our model, Satellite Neural Graphics Primitives (SAT-NGP) decreases the learning time to 15 minutes while maintaining the quality of the 3D reconstruction.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- SPARSESAT-NERF: DENSE DEPTH SUPERVISED NEURAL RADIANCE FIELDS FOR SPARSE SATELLITE IMAGESISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2023
- Remote Sensing Neural Radiance Fields for Multi-View Satellite PhotogrammetryRemote Sensing, 2023
- RobustNeRF: Ignoring Distractors with Robust Losses2023
- Multi-Date Earth Observation NeRF: The Detail Is in the Shadows2023
- Instant neural graphics primitives with a multiresolution hash encodingACM Transactions on Graphics, 2022
- Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras2022
- NeRFCommunications of the ACM, 2021
- NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections2021
- Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry2021
- A NEW SATELLITE IMAGERY STEREO PIPELINE DESIGNED FOR SCALABILITY, ROBUSTNESS AND PERFORMANCEISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020