Reproduce “SAR-NeRF: Neural Radiance Fields for Synthetic Aperture Radar Multi-View Representation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zhengxin Lei, Feng Xu, Jiangtao Wei, Feng Cai, Feng Wang, Ya-Qiu Jin
SAR-NeRF synthesizes synthetic-aperture radar views to augment target-recognition training when images are scarce and vary with viewing angle. It maps observations into a 3D voxel field, estimates attenuation and scattering, and renders images using SAR geometry. On 10-class MSTAR classification with ResNet50 and 12 images per class, augmentation raised accuracy from 85.2% to 91.6%; this result is specific to setup.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.