Normal-guided Detail-Preserving Neural Implicit Function for High-Fidelity 3D Surface Reconstruction

Abstract

Neural implicit representations have emerged as a powerful paradigm for 3D reconstruction. However, despite their success, existing methods fail to capture fine geometric details and thin structures, especially in scenarios where only sparse multi-view RGB images of the objects of interest are available. This paper shows that training neural representations with first-order differential properties (surface normals) leads to highly accurate 3D surface reconstruction, even with as few as two RGB images. Using input RGB images, we compute approximate ground-truth surface normals from depth maps produced by an off-the-shelf monocular depth estimator. During training, we directly locate the surface point of the SDF network and supervise its normal with the one estimated from the depth map. Extensive experiments demonstrate that our method achieves state-of-the-art reconstruction accuracy with a minimal number of views, capturing intricate geometric details and thin structures that were previously challenging to capture.

Accepted at ACM SIGGRAPH I3D 2025. Published in PACMCGIT journal. Project page with images and code: https://graphics-research-group.github.io/sn-nir

References in corpus (12)

• Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
• A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
• MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction
• Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
• NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
• Implicit Geometric Regularization for Learning Shapes
• Neural Unsigned Distance Fields for Implicit Function Learning
• Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
• BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
• UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene
• SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration