SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies

TL;DR

SparseRecon is a neural implicit surface reconstruction method that effectively utilizes feature and depth consistency constraints to produce high-quality 3D reconstructions from sparse views, outperforming existing approaches especially with limited overlapping views.

Contribution

The paper introduces SparseRecon, a novel approach combining feature consistency and uncertainty-guided depth constraints for improved sparse-view surface reconstruction.

Findings

Outperforms state-of-the-art methods in sparse-view scenarios

Produces high-quality geometry with limited overlapping views

Effectively handles occlusions and view inconsistencies

Abstract

Surface reconstruction from sparse views aims to reconstruct a 3D shape or scene from few RGB images. The latest methods are either generalization-based or overfitting-based. However, the generalization-based methods do not generalize well on views that were unseen during training, while the reconstruction quality of overfitting-based methods is still limited by the limited geometry clues. To address this issue, we propose SparseRecon, a novel neural implicit reconstruction method for sparse views with volume rendering-based feature consistency and uncertainty-guided depth constraint. Firstly, we introduce a feature consistency loss across views to constrain the neural implicit field. This design alleviates the ambiguity caused by insufficient consistency information of views and ensures completeness and smoothness in the reconstruction results. Secondly, we employ an uncertainty-guided depth constraint to back up the feature consistency loss in areas with occlusion and insignificant features, which recovers geometry details for better reconstruction quality. Experimental results demonstrate that our method outperforms the state-of-the-art methods, which can produce high-quality geometry with sparse-view input, especially in the scenarios with small overlapping views. Project page: https://hanl2010.github.io/SparseRecon/.