Sparis: Neural Implicit Surface Reconstruction of Indoor Scenes from Sparse Views

TL;DR

Sparis introduces a novel inter-image matching prior and filtering strategies to improve neural implicit surface reconstruction of indoor scenes from limited views, outperforming existing methods on benchmark datasets.

Contribution

The paper presents a new inter-image matching prior and filtering techniques that enhance sparse-view indoor scene reconstruction with neural implicit surfaces.

Findings

Outperforms existing methods on benchmark datasets.

Effective in reconstructing scenes from limited views.

Improves depth accuracy and cross-view consistency.

Abstract

In recent years, reconstructing indoor scene geometry from multi-view images has achieved encouraging accomplishments. Current methods incorporate monocular priors into neural implicit surface models to achieve high-quality reconstructions. However, these methods require hundreds of images for scene reconstruction. When only a limited number of views are available as input, the performance of monocular priors deteriorates due to scale ambiguity, leading to the collapse of the reconstructed scene geometry. In this paper, we propose a new method, named Sparis, for indoor surface reconstruction from sparse views. Specifically, we investigate the impact of monocular priors on sparse scene reconstruction, introducing a novel prior based on inter-image matching information. Our prior offers more accurate depth information while ensuring cross-view matching consistency. Additionally, we employ an angular filter strategy and an epipolar matching weight function, aiming to reduce errors due to view matching inaccuracies, thereby refining the inter-image prior for improved reconstruction accuracy. The experiments conducted on widely used benchmarks demonstrate superior performance in sparse-view scene reconstruction.