ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction

Neural implicit reconstruction via volume rendering has demonstrated its effectiveness in recovering dense 3D surfaces. However, it is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with differing characteristics. To address this issue, previous methods typically employ geometric priors, which are often constrained by the performance of the prior models. In this paper, we propose ND-SDF, which learns a Normal Deflection field to represent the angular deviation between the scene normal and the prior normal. Unlike previous methods that uniformly apply geometric priors on all samples, introducing significant bias in accuracy, our proposed normal deflection field dynamically learns and adapts the utilization of samples based on their specific characteristics, thereby improving both the accuracy and effectiveness of the model. Our method not only obtains smooth weakly textured regions such as walls and floors but also preserves the geometric details of complex structures. In addition, we introduce a novel ray sampling strategy based on the deflection angle to facilitate the unbiased rendering process, which significantly improves the quality and accuracy of intricate surfaces, especially on thin structures. Consistent improvements on various challenging datasets demonstrate the superiority of our method.

Overview of our method. We utilize multi-resolution hash grids γL as scene representation. The core of ND-SDF is the normal deflection field. We represent deflection with quaternions, which are predicted by the deflection network (denoted as fd). We align the deflected normals with the prior normals to learn the deviation between the scene and the priors. To distinctly supervise high and low-frequency areas, we employ an adaptive deflection angle prior loss, ensuring both smoothness and detail. Furthermore, we utilize the deflection angle Δθ to distinguish complex structures, enabling angle-guided sampling and color loss to facilitate intricate surface details. Lastly, we combine the unbiased rendering method (TUVR) to promote the generation of extremely thin structures indoors.