通过360度球面射线增强，提升少样本NeRF的视角多样性与一致性。
DivCon-NeRF: Diverse and Consistent Ray Augmentation for Few-Shot NeRF
- 用以表面点为中心的虚拟球生成全向射线，增强多样性
- 通过一致性掩码过滤异常射线，显著减少浮点和畸变
- 兼容多种少样本NeRF方法，适用于真实场景重建
神经辐射场（NeRF）在新视角合成中表现优异，但需大量多视角图像，限制了其在少样本场景中的应用。射线增强可缓解稀疏数据导致的过拟合问题，但现有方法仅在原射线附近生成新射线，因视角有限且受近处障碍物和复杂表面遮挡，易产生浮点和外观畸变。为此，我们提出DivCon-NeRF，引入基于球面的射线增强方法，显著提升多样性和一致性。通过以预测表面点为中心的虚拟球，从360度方向生成多样化射线，并利用一致性掩码有效剔除不一致射线。设计针对性损失函数，充分利用这些增强射线，有效减少浮点和视觉畸变。实验表明，该方法在Blender、LLFF、DTU数据集上优于近期少样本NeRF方法。此外，DivCon-NeRF具有强泛化能力，可有效集成于基于正则化和框架改进的少样本NeRF模型中。
原文摘要 · Abstract (English)
Neural Radiance Field (NeRF) has shown remarkable performance in novel view synthesis but requires numerous multi-view images, limiting its practicality in few-shot scenarios. Ray augmentation has been proposed to alleviate overfitting caused by sparse training data by generating additional rays. However, existing methods, which generate augmented rays only near the original rays, exhibit pronounced floaters and appearance distortions due to limited viewpoints and inconsistent rays obstructed by nearby obstacles and complex surfaces. To address these problems, we propose DivCon-NeRF, which introduces novel sphere-based ray augmentations to significantly enhance both diversity and consistency. By employing a virtual sphere centered at the predicted surface point, our method generates diverse augmented rays from all 360-degree directions, facilitated by our consistency mask that effectively filters out inconsistent rays. We introduce tailored loss functions that leverage these augmentations, effectively reducing floaters and visual distortions. Consequently, our method outperforms recent few-shot NeRF approaches on the Blender, LLFF, and DTU datasets. Furthermore, DivCon-NeRF demonstrates strong generalizability by effectively integrating with both regularization- and framework-based few-shot NeRFs.
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。