Learning Neural Implicit Representations with Surface Signal Parameterizations
This work addresses a key limitation in neural implicit representations for 3D object modeling, enabling compatibility with existing mesh-based digital content and texture mapping applications, though it is incremental as it builds on prior overfitting methods.
The paper tackles the problem of applying texture mapping to neural implicit surface representations, which lack configurable surface parameterizations, by designing a neural network architecture that implicitly encodes surface parameterization for appearance data, achieving performance that outperforms baselines and state-of-the-art alternatives.
Neural implicit surface representations have recently emerged as popular alternative to explicit 3D object encodings, such as polygonal meshes, tabulated points, or voxels. While significant work has improved the geometric fidelity of these representations, much less attention is given to their final appearance. Traditional explicit object representations commonly couple the 3D shape data with auxiliary surface-mapped image data, such as diffuse color textures and fine-scale geometric details in normal maps that typically require a mapping of the 3D surface onto a plane, i.e., a surface parameterization; implicit representations, on the other hand, cannot be easily textured due to lack of configurable surface parameterization. Inspired by this digital content authoring methodology, we design a neural network architecture that implicitly encodes the underlying surface parameterization suitable for appearance data. As such, our model remains compatible with existing mesh-based digital content with appearance data. Motivated by recent work that overfits compact networks to individual 3D objects, we present a new weight-encoded neural implicit representation that extends the capability of neural implicit surfaces to enable various common and important applications of texture mapping. Our method outperforms reasonable baselines and state-of-the-art alternatives.