用离散小波变换提升少样本神经辐射场的训练速度与质量
DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform
- 引入小波损失函数，优先学习低频信息，缓解早期过拟合
- 3视图下在LLFF上PSNR提升15.07%，LPIPS降低36.30%
- 适用于快速收敛的隐式表示，如Instant-NGP或3DGS
神经辐射场（NeRF）在新视角合成与三维场景表示中表现优异，但其实际应用受限于收敛慢和对密集训练视图的依赖。为此，我们提出DWTNeRF，一种基于Instant-NGP快速训练哈希编码的统一框架，结合专为少样本NeRF设计的正则化项，可在稀疏训练视图下运行。DWTNeRF引入一种新颖的离散小波损失，可直接在训练目标中显式优先处理低频信息，减少少样本NeRF在早期训练阶段对高频信息的过拟合。我们还提出一种基于多头注意力的模型方法，兼容Instant-NGP且对架构变化不敏感。在3视图的LLFF基准测试中，DWTNeRF相比原始Instant-NGP在PSNR上提升15.07%，SSIM提升24.45%，LPIPS降低36.30%。该方法促使重新思考当前针对快速收敛隐式表示（如Instant-NGP或3DGS）的少样本策略。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。