A Robust Segmentation Algorithmfor for 3D Complex Meshes
Authors:
Open Access
- 1 March 2021
- conference paper
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1802 (3) , 032045
Abstract
Segmenting 3D mesh is a difficult topic in computer graphics. This paper proposes a new mesh segmentation algorithm. First, we over-segment the input mesh to generate a series of superfacets. Second, we introduce a novel region fusion algorithm to obtain the segmentation result. Various experiments show that our algorithm is able to handle 3D meshes with complex shape and rich details. Even though the input mesh has noises or holes our algorithm can still achieve satisfactory results.Keywords
This publication has 11 references indexed in Scilit:
- 3D Mesh Labeling via Deep Convolutional Neural NetworksACM Transactions on Graphics, 2015
- Dot Scissor: A Single-Click Interface for Mesh SegmentationIEEE Transactions on Visualization and Computer Graphics, 2011
- Mesh Segmentation with Concavity-Aware FieldsIEEE Transactions on Visualization and Computer Graphics, 2011
- Mesh Decomposition with Cross‐Boundary BrushesComputer Graphics Forum, 2010
- A benchmark for 3D mesh segmentationACM Transactions on Graphics, 2009
- A Concise and Provably Informative Multi‐Scale Signature Based on Heat DiffusionComputer Graphics Forum, 2009
- Randomized cuts for 3D mesh analysisACM Transactions on Graphics, 2008
- Consistent mesh partitioning and skeletonisation using the shape diameter functionThe Visual Computer, 2008
- Easy Mesh CuttingComputer Graphics Forum, 2006
- Hierarchical mesh decomposition using fuzzy clustering and cutsACM Transactions on Graphics, 2003