PANeRF: Pseudo-view Augmentation for Improved Neural Radiance Fields Based on Few-shot Inputs
This addresses the challenge of reducing the number of input views needed for NeRF, which is important for applications in 3D scene reconstruction and visualization, though it appears incremental as it builds on existing NeRF methods.
The paper tackles the problem of neural radiance fields (NeRF) requiring dense input views for high-quality novel-view synthesis by proposing pseudo-view augmentation to improve rendering with few-shot inputs, achieving superior quality and outperforming existing methods in experiments.
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.