AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction

TL;DR

AniSDF introduces a fused-granularity neural surface model with anisotropic encoding that achieves high-fidelity 3D reconstruction and realistic rendering, balancing geometric accuracy and visual quality.

Contribution

The paper proposes a novel fused-granularity neural surface with physics-based anisotropic encoding for improved geometry and rendering quality in 3D reconstruction.

Findings

Significantly improves geometry reconstruction accuracy.

Enhances novel-view synthesis quality.

Works effectively on complex structures without extensive hyperparameter tuning.

Abstract

Neural radiance fields have recently revolutionized novel-view synthesis and achieved high-fidelity renderings. However, these methods sacrifice the geometry for the rendering quality, limiting their further applications including relighting and deformation. How to synthesize photo-realistic rendering while reconstructing accurate geometry remains an unsolved problem. In this work, we present AniSDF, a novel approach that learns fused-granularity neural surfaces with physics-based encoding for high-fidelity 3D reconstruction. Different from previous neural surfaces, our fused-granularity geometry structure balances the overall structures and fine geometric details, producing accurate geometry reconstruction. To disambiguate geometry from reflective appearance, we introduce blended radiance fields to model diffuse and specularity following the anisotropic spherical Gaussian encoding, a physics-based rendering pipeline. With these designs, AniSDF can reconstruct objects with complex structures and produce high-quality renderings. Furthermore, our method is a unified model that does not require complex hyperparameter tuning for specific objects. Extensive experiments demonstrate that our method boosts the quality of SDF-based methods by a great scale in both geometry reconstruction and novel-view synthesis.