HR-NeuS: Recovering High-Frequency Surface Geometry via Neural Implicit Surfaces
This addresses the need for detailed 3D surface reconstruction in computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of over-smoothed geometries in neural implicit surface reconstruction by introducing HR-NeuS, which recovers high-frequency surface details while maintaining large-scale accuracy, as demonstrated on DTU and BlendedMVS datasets with qualitative improvements and similar quantitative accuracy.
Recent advances in neural implicit surfaces for multi-view 3D reconstruction primarily focus on improving large-scale surface reconstruction accuracy, but often produce over-smoothed geometries that lack fine surface details. To address this, we present High-Resolution NeuS (HR-NeuS), a novel neural implicit surface reconstruction method that recovers high-frequency surface geometry while maintaining large-scale reconstruction accuracy. We achieve this by utilizing (i) multi-resolution hash grid encoding rather than positional encoding at high frequencies, which boosts our model's expressiveness of local geometry details; (ii) a coarse-to-fine algorithmic framework that selectively applies surface regularization to coarse geometry without smoothing away fine details; (iii) a coarse-to-fine grid annealing strategy to train the network. We demonstrate through experiments on DTU and BlendedMVS datasets that our approach produces 3D geometries that are qualitatively more detailed and quantitatively of similar accuracy compared to previous approaches.