FourieRF: Few-Shot NeRFs via Progressive Fourier Frequency Control
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_ | 1866909473419821056 |
|---|---|
| author | Gomez, Diego Gong, Bingchen Ovsjanikov, Maks |
| author_facet | Gomez, Diego Gong, Bingchen Ovsjanikov, Maks |
| contents | In this work, we introduce FourieRF, a novel approach for achieving fast and high-quality reconstruction in the few-shot setting. Our method effectively parameterizes features through an explicit curriculum training procedure, incrementally increasing scene complexity during optimization. Experimental results show that the prior induced by our approach is both robust and adaptable across a wide variety of scenes, establishing FourieRF as a strong and versatile baseline for the few-shot rendering problem. While our approach significantly reduces artifacts, it may still lead to reconstruction errors in severely under-constrained scenarios, particularly where view occlusion leaves parts of the shape uncovered. In the future, our method could be enhanced by integrating foundation models to complete missing parts using large data-driven priors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01405 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FourieRF: Few-Shot NeRFs via Progressive Fourier Frequency Control Gomez, Diego Gong, Bingchen Ovsjanikov, Maks Computer Vision and Pattern Recognition In this work, we introduce FourieRF, a novel approach for achieving fast and high-quality reconstruction in the few-shot setting. Our method effectively parameterizes features through an explicit curriculum training procedure, incrementally increasing scene complexity during optimization. Experimental results show that the prior induced by our approach is both robust and adaptable across a wide variety of scenes, establishing FourieRF as a strong and versatile baseline for the few-shot rendering problem. While our approach significantly reduces artifacts, it may still lead to reconstruction errors in severely under-constrained scenarios, particularly where view occlusion leaves parts of the shape uncovered. In the future, our method could be enhanced by integrating foundation models to complete missing parts using large data-driven priors. |
| title | FourieRF: Few-Shot NeRFs via Progressive Fourier Frequency Control |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.01405 |