NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction
This work improves surface reconstruction for 3D modeling applications, but it is incremental as it builds on existing differentiable ray casting methods.
The paper tackles the problem of high-fidelity implicit surface reconstruction by addressing limitations in capturing sharp local topologies like small holes, resulting in promising mesh surfaces as demonstrated on DTU and BlendedMVS datasets.
This paper studies implicit surface reconstruction leveraging differentiable ray casting. Previous works such as IDR and NeuS overlook the spatial context in 3D space when predicting and rendering the surface, thereby may fail to capture sharp local topologies such as small holes and structures. To mitigate the limitation, we propose a flexible neural implicit representation leveraging hierarchical voxel grids, namely Neural Deformable Anchor (NeuDA), for high-fidelity surface reconstruction. NeuDA maintains the hierarchical anchor grids where each vertex stores a 3D position (or anchor) instead of the direct embedding (or feature). We optimize the anchor grids such that different local geometry structures can be adaptively encoded. Besides, we dig into the frequency encoding strategies and introduce a simple hierarchical positional encoding method for the hierarchical anchor structure to flexibly exploit the properties of high-frequency and low-frequency geometry and appearance. Experiments on both the DTU and BlendedMVS datasets demonstrate that NeuDA can produce promising mesh surfaces.