FourieRF: Few-Shot NeRFs via Progressive Fourier Frequency Control
This addresses the few-shot rendering problem for 3D reconstruction applications, presenting an incremental improvement over existing methods.
The paper tackles the problem of fast, high-quality 3D scene reconstruction from few images using neural radiance fields (NeRFs), achieving robust and adaptable performance across diverse scenes with significantly reduced artifacts.
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.