Paper ID: 2312.08364
View-Dependent Octree-based Mesh Extraction in Unbounded Scenes for Procedural Synthetic Data
Zeyu Ma, Alexander Raistrick, Lahav Lipson, Jia Deng
Procedural synthetic data generation has received increasing attention in computer vision. Procedural signed distance functions (SDFs) are a powerful tool for modeling large-scale detailed scenes, but existing mesh extraction methods have artifacts or performance profiles that limit their use for synthetic data. We propose OcMesher, a mesh extraction algorithm that efficiently handles high-detail unbounded scenes with perfect view-consistency, with easy export to downstream real-time engines. The main novelty of our solution is an algorithm to construct an octree based on a given SDF and multiple camera views. We performed extensive experiments, and show our solution produces better synthetic data for training and evaluation of computer vision models.
Submitted: Dec 13, 2023