The method of neural radiance fields (NeRF) has been developed in recent years, and this technology has promising applications for synthesizing novel views of complex scenes. However, NeRF requires dense input views, typically numbering in the hundreds, for generating high-quality images. With a decrease in the number of input views, the rendering quality of NeRF for unseen viewpoints tends to degenerate drastically. To overcome this challenge, we propose pseudo-view augmentation of NeRF, a scheme that expands a sufficient amount of data by considering the geometry of few-shot inputs. We first initialized the NeRF network by leveraging the expanded pseudo-views, which efficiently minimizes uncertainty when rendering unseen views. Subsequently, we fine-tuned the network by utilizing sparse-view inputs containing precise geometry and color information. Through experiments under various settings, we verified that our model faithfully synthesizes novel-view images of superior quality and outperforms existing methods for multi-view datasets.
翻译:近些年来开发了神经光亮场的方法( NERF ), 这一技术在综合复杂场景的新观点方面有良好的应用。 然而, NERF 需要大量输入视图, 通常以数百计, 以生成高质量的图像。 随着输入视图数量的减少, NERF 的无形观点质量的提高会急剧下降。 为了克服这一挑战, 我们提出了 NERF 的假视图增强方案, 这个方案通过考虑少见投入的几何测量法来扩大足够数量的数据。 我们首先利用扩大的假视图来初始化NERF 网络, 从而有效地将隐形视图的不确定性降到最低。 随后, 我们通过利用包含精确的几何和颜色信息的稀有视图来调整网络。 我们通过在各种环境下的实验, 验证我们的模型忠实地合成了高质量的新视图图像, 并超越了多视图数据集的现有方法 。