BundleRecon: Ray Bundle-Based 3D Neural Reconstruction

TL;DR

BundleRecon introduces a novel ray bundle sampling approach that leverages neighboring pixel information to enhance 3D neural reconstruction quality in multi-view settings.

Contribution

It proposes a new ray bundle sampling method and bundle-based constraints to improve neural implicit multi-view reconstruction.

Findings

Improves reconstruction quality over existing methods.

Compatible with current neural reconstruction frameworks.

Demonstrates significant enhancement in experimental results.

Abstract

With the growing popularity of neural rendering, there has been an increasing number of neural implicit multi-view reconstruction methods. While many models have been enhanced in terms of positional encoding, sampling, rendering, and other aspects to improve the reconstruction quality, current methods do not fully leverage the information among neighboring pixels during the reconstruction process. To address this issue, we propose an enhanced model called BundleRecon. In the existing approaches, sampling is performed by a single ray that corresponds to a single pixel. In contrast, our model samples a patch of pixels using a bundle of rays, which incorporates information from neighboring pixels. Furthermore, we design bundle-based constraints to further improve the reconstruction quality. Experimental results demonstrate that BundleRecon is compatible with the existing neural implicit multi-view reconstruction methods and can improve their reconstruction quality.