PhysicsNeRF is a physically grounded framework for 3D reconstruction from sparse views, extending Neural Radiance Fields with four complementary constraints: depth ranking, RegNeRF-style consistency, sparsity priors, and cross-view alignment. While standard NeRFs fail under sparse supervision, PhysicsNeRF employs a compact 0.67M-parameter architecture and achieves 21.4 dB average PSNR using only 8 views, outperforming prior methods. A generalization gap of 5.7-6.2 dB is consistently observed and analyzed, revealing fundamental limitations of sparse-view reconstruction. PhysicsNeRF enables physically consistent, generalizable 3D representations for agent interaction and simulation, and clarifies the expressiveness-generalization trade-off in constrained NeRF models.
@article{arxiv.2505.23481,
title = {PhysicsNeRF: Physics-Guided 3D Reconstruction from Sparse Views},
author = {Mohamed Rayan Barhdadi and Hasan Kurban and Hussein Alnuweiri},
journal= {arXiv preprint arXiv:2505.23481},
year = {2025}
}
Comments
4 pages, 2 figures, 2 tables. Appearing in Building Physically Plausible World Models at the 42nd International Conference on Machine Learning (ICML 2025), Vancouver, Canada