SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization

Understand

3D surface reconstruction from images is essential for numerous applications.

• Recently, Neural Radiance Fields (NeRFs) have emerged as a promising framework for 3D modeling.
• However, NeRFs require accurate camera poses as input, and existing methods struggle to handle significantly noisy pose estimates (i.e., outliers), which are commonly encountered in real-world scenarios.
• To tackle this challenge, we present a novel approach that optimizes radiance fields with scene graphs to mitigate the influence of outlier poses.