DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform
This work addresses the practical limitation of NeRF for applications requiring sparse views, offering a domain-specific improvement for 3D scene synthesis.
The paper tackles the problem of slow convergence and reliance on dense training views in Neural Radiance Fields (NeRF) by proposing DWTNeRF, a framework that improves few-shot NeRF performance, achieving gains of 15.07% in PSNR, 24.45% in SSIM, and 36.30% in LPIPS on the 3-shot LLFF benchmark.
Neural Radiance Fields (NeRF) has achieved superior performance in novel view synthesis and 3D scene representation, but its practical applications are hindered by slow convergence and reliance on dense training views. To this end, we present DWTNeRF, a unified framework based on Instant-NGP's fast-training hash encoding. It is coupled with regularization terms designed for few-shot NeRF, which operates on sparse training views. Our DWTNeRF additionally includes a novel Discrete Wavelet loss that allows explicit prioritization of low frequencies directly in the training objective, reducing few-shot NeRF's overfitting on high frequencies in earlier training stages. We also introduce a model-based approach, based on multi-head attention, that is compatible with INGP, which are sensitive to architectural changes. On the 3-shot LLFF benchmark, DWTNeRF outperforms Vanilla INGP by 15.07% in PSNR, 24.45% in SSIM and 36.30% in LPIPS. Our approach encourages a re-thinking of current few-shot approaches for fast-converging implicit representations like INGP or 3DGS.