CVAug 14, 2019

Directional TSDF: Modeling Surface Orientation for Coherent Meshes

arXiv:1908.05146v17 citations
AI Analysis

This addresses a specific issue in robotic applications like object modeling and mapping where thin structures cause severe reconstruction errors.

The paper tackles the problem of inaccurate 3D reconstruction of thin structures in real-time RGB-D sensor data by proposing a directional TSDF representation that stores opposite surfaces separately and modifying the marching cubes algorithm. The result is a method that outperforms state-of-the-art TSDF algorithms in mesh accuracy.

Real-time 3D reconstruction from RGB-D sensor data plays an important role in many robotic applications, such as object modeling and mapping. The popular method of fusing depth information into a truncated signed distance function (TSDF) and applying the marching cubes algorithm for mesh extraction has severe issues with thin structures: not only does it lead to loss of accuracy, but it can generate completely wrong surfaces. To address this, we propose the directional TSDF - a novel representation that stores opposite surfaces separate from each other. The marching cubes algorithm is modified accordingly to retrieve a coherent mesh representation. We further increase the accuracy by using surface gradient-based ray casting for fusing new measurements. We show that our method outperforms state-of-the-art TSDF reconstruction algorithms in mesh accuracy.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes