NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views
This addresses the challenge of accurate 3D surface reconstruction from limited camera views, which is crucial for applications like robotics and AR/VR, though it is an incremental advance over prior sparse-view methods.
The paper tackles the problem of neural surface reconstruction from sparse input views, which existing methods struggle with due to high training costs and limited perspectives. It proposes NeuSurf, a framework using on-surface priors, achieving significant improvements over state-of-the-art methods on DTU and BlendedMVS datasets in sparse settings.
Recently, neural implicit functions have demonstrated remarkable results in the field of multi-view reconstruction. However, most existing methods are tailored for dense views and exhibit unsatisfactory performance when dealing with sparse views. Several latest methods have been proposed for generalizing implicit reconstruction to address the sparse view reconstruction task, but they still suffer from high training costs and are merely valid under carefully selected perspectives. In this paper, we propose a novel sparse view reconstruction framework that leverages on-surface priors to achieve highly faithful surface reconstruction. Specifically, we design several constraints on global geometry alignment and local geometry refinement for jointly optimizing coarse shapes and fine details. To achieve this, we train a neural network to learn a global implicit field from the on-surface points obtained from SfM and then leverage it as a coarse geometric constraint. To exploit local geometric consistency, we project on-surface points onto seen and unseen views, treating the consistent loss of projected features as a fine geometric constraint. The experimental results with DTU and BlendedMVS datasets in two prevalent sparse settings demonstrate significant improvements over the state-of-the-art methods.