A Benchmark for 3D Mesh Segmentation
ACM Transactions on Graphics (Proc. SIGGRAPH), August 2009
Composite images of segment boundaries selected by different people (the darker the seam the more people have chosen a cut along that edge). One example is shown for each of the 19 object categories considered in this study.
Abstract
This paper describes a benchmark for evaluation of 3D mesh
segmentation algorithms. The benchmark comprises a data set with
4,300 manually generated segmentations for 380 surface meshes of 19
different object categories, and it includes software for analyzing 11
geometric properties of segmentations and producing 4 quantitative
metrics for comparison of segmentations. The paper investigates the
design decisions made in building the benchmark, analyzes properties
of human-generated and computer-generated segmentations, and provides
quantitative comparisons of 7 recently published mesh segmentation
algorithms. Our results suggest that people are remarkably consistent
in the way that they segment most 3D surface meshes, that no one
automatic segmentation algorithm is better than the others for all
types of objects, and that algorithms based on non-local shape
features seem to produce segmentations that most closely resemble ones
made by humans.
Files
- Paper (PDF, 1MB)
Additional Links
Citation
Xiaobai Chen, Aleksey Golovinskiy, and Thomas Funkhouser.
"A Benchmark for 3D Mesh Segmentation."
ACM Transactions on Graphics (Proc. SIGGRAPH) 28(3), August 2009.
BibTeX
@article{Chen:2009:ABF, author = "Xiaobai Chen and Aleksey Golovinskiy and Thomas Funkhouser", title = "A Benchmark for {3D} Mesh Segmentation", journal = "ACM Transactions on Graphics (Proc. SIGGRAPH)", year = "2009", month = aug, volume = "28", number = "3" }