SFS-NeRF: Enhancing Geometry Consistency in Few-Shot Novel View Synthesis Through Surface-Aware Neural Rendering

We propose a new pipeline for few-shot novel view synthesis called Surface-aware Few-Shot Neural Radiance Fields (SFS-NeRF). This approach enhances surface rigidity, resulting in more realistic rendering outcomes. Our model uti-lizes geometric constraints to better maintain the rigid surface of objects, effectively addressing the limitations encountered in previous methods that rely on sparse inputs. To achieve accurate color reconstruction of rendered images based on viewing direction, we employ Spherical Harmonics (SH) parameters. Additionally, we use the Laplace distribution to model the transparency function, which offers sharper max-ima compared to the logistic sigmoid distribution used in earlier works. During the training phase, we implement occlusion regularization and frequency regularization to further improve both the training and rendering processes. Experiments show that our method outperforms the baseline model on both the Blender and DTU datasets.