SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance

TL;DR

SGCNeRF introduces a novel sparse geometric regularization method with frequency guidance, significantly improving few-shot neural rendering quality by preserving high-frequency details and enhancing geometry consistency.

Contribution

It proposes a new feature-matching-based regularization module with frequency-guided strategies, advancing few-shot neural rendering beyond existing methods like FreeNeRF.

Findings

Achieves 0.7 dB higher PSNR on LLFF and DTU datasets.

Effectively preserves high-frequency structural details.

Outperforms FreeNeRF in geometry consistency and rendering quality.

Abstract

Neural Radiance Field (NeRF) technology has made significant strides in creating novel viewpoints. However, its effectiveness is hampered when working with sparsely available views, often leading to performance dips due to overfitting. FreeNeRF attempts to overcome this limitation by integrating implicit geometry regularization, which incrementally improves both geometry and textures. Nonetheless, an initial low positional encoding bandwidth results in the exclusion of high-frequency elements. The quest for a holistic approach that simultaneously addresses overfitting and the preservation of high-frequency details remains ongoing. This study presents a novel feature-matching-based sparse geometry regularization module, enhanced by a spatially consistent geometry filtering mechanism and a frequency-guided geometric regularization strategy. This module excels at accurately identifying high-frequency keypoints, effectively preserving fine structural details. Through progressive refinement of geometry and textures across NeRF iterations, we unveil an effective few-shot neural rendering architecture, designated as SGCNeRF, for enhanced novel view synthesis. Our experiments demonstrate that SGCNeRF not only achieves superior geometry-consistent outcomes but also surpasses FreeNeRF, with improvements of 0.7 dB in PSNR on LLFF and DTU.