SurfelMeshing: Online Surfel-Based Mesh Reconstruction

TL;DR

SurfelMeshing introduces an online surfel-based method for mesh reconstruction from RGB-D video that adapts quickly to scene changes and supports detailed, thin, and high-resolution surface reconstructions without volumetric fusion.

Contribution

It presents a novel surfel-based approach for real-time mesh reconstruction that handles loop closures and varying scan resolutions more effectively than volumetric methods.

Findings

Produces competitive reconstructions compared to state-of-the-art methods.

Supports reconstruction of thin objects and high-resolution surface details.

Maintains dense surface representation during SLAM with quick adaptation to scene changes.

Abstract

We address the problem of mesh reconstruction from live RGB-D video, assuming a calibrated camera and poses provided externally (e.g., by a SLAM system). In contrast to most existing approaches, we do not fuse depth measurements in a volume but in a dense surfel cloud. We asynchronously (re)triangulate the smoothed surfels to reconstruct a surface mesh. This novel approach enables to maintain a dense surface representation of the scene during SLAM which can quickly adapt to loop closures. This is possible by deforming the surfel cloud and asynchronously remeshing the surface where necessary. The surfel-based representation also naturally supports strongly varying scan resolution. In particular, it reconstructs colors at the input camera's resolution. Moreover, in contrast to many volumetric approaches, ours can reconstruct thin objects since objects do not need to enclose a volume. We demonstrate our approach in a number of experiments, showing that it produces reconstructions that are competitive with the state-of-the-art, and we discuss its advantages and limitations. The algorithm (excluding loop closure functionality) is available as open source at https://github.com/puzzlepaint/surfelmeshing .