SurfelMeshing: Online Surfel-Based Mesh Reconstruction

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 .

Version accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence

Cited by in corpus (11)

• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
• From SLAM to Situational Awareness: Challenges and Survey
• Augmenting Colonoscopy using Extended and Directional CycleGAN for Lossy Image Translation
• HRBF-Fusion: Accurate 3D reconstruction from RGB-D data using on-the-fly implicits
• GSORB-SLAM: Gaussian Splatting SLAM benefits from ORB features and Transmittance information
• LiveNVS: Neural View Synthesis on Live RGB-D Streams
• AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenes
• Online Learning of a Probabilistic and Adaptive Scene Representation
• Splat-based 3D Scene Reconstruction with Extreme Motion-blur
• RGB-D SLAM with Structural Regularities
• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies