PhysicsNeRF: Physics-Guided 3D Reconstruction from Sparse Views
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911018381213696 |
|---|---|
| author | Barhdadi, Mohamed Rayan Kurban, Hasan Alnuweiri, Hussein |
| author_facet | Barhdadi, Mohamed Rayan Kurban, Hasan Alnuweiri, Hussein |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23481 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PhysicsNeRF: Physics-Guided 3D Reconstruction from Sparse Views Barhdadi, Mohamed Rayan Kurban, Hasan Alnuweiri, Hussein Computer Vision and Pattern Recognition I.2.10; I.4.8; I.5.1 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. |
| title | PhysicsNeRF: Physics-Guided 3D Reconstruction from Sparse Views |
| topic | Computer Vision and Pattern Recognition I.2.10; I.4.8; I.5.1 |
| url | https://arxiv.org/abs/2505.23481 |