无需预训练先验，快速实现极少量图像的3D场景重建。
FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors
- 通过多尺度权重共享体素表示场景细节
- 利用重投影误差选择伪真值深度，加速收敛
- 适合资源有限下需快速高精度重建的场景
Neural Radiance Fields (NeRF) 在极端少样本场景下面临过拟合和训练时间长的问题。现有方法如 FreeNeRF 和 SparseNeRF 依赖频率正则化或预训练先验，但存在复杂调度与偏差问题。本文提出 FrugalNeRF，一种新型少样本 NeRF 框架，通过多尺度间共享权重体素高效表示场景细节。核心创新在于跨尺度几何自适应机制，基于重投影误差在不同尺度间选择伪真值深度，引导训练过程而不依赖外部学习的先验，充分挖掘训练数据潜力。该方法还可融合预训练先验，在不减慢收敛速度的前提下提升重建质量。在 LLFF、DTU 与 RealEstate-10K 数据集上的实验表明，FrugalNeRF 显著优于其他少样本 NeRF 方法，同时大幅缩短训练时间，是高效且精准的3D场景重建实用方案。
原文摘要 · Abstract (English)
Neural Radiance Fields (NeRF) face significant challenges in extreme few-shot scenarios, primarily due to overfitting and long training times. Existing methods, such as FreeNeRF and SparseNeRF, use frequency regularization or pre-trained priors but struggle with complex scheduling and bias. We introduce FrugalNeRF, a novel few-shot NeRF framework that leverages weight-sharing voxels across multiple scales to efficiently represent scene details. Our key contribution is a cross-scale geometric adaptation scheme that selects pseudo ground truth depth based on reprojection errors across scales. This guides training without relying on externally learned priors, enabling full utilization of the training data. It can also integrate pre-trained priors, enhancing quality without slowing convergence. Experiments on LLFF, DTU, and RealEstate-10K show that FrugalNeRF outperforms other few-shot NeRF methods while significantly reducing training time, making it a practical solution for efficient and accurate 3D scene reconstruction.
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。