I'm wondering what benchmarks there exist for semantic segmentation of 3D meshes? I have already found "A Benchmark for 3D Mesh Segmentation"; is this currently the only benchmark that exists for 3D mesh segmentation?

Also, is there some list of state-of-the-art methods for semantic segmentation of 3D meshes, like there is for some other benchmarks?


1 Answer 1



Currently there seems to be a preference for using point clouds over raw meshes for 3d segmentation. They can use all the benchmarks below plus:

  1. S3DIS URL: http://buildingparser.stanford.edu/dataset.html
  2. ScanNet URL: http://www.scan-net.org/

The state of the art seems to be [11] closely followed by [10] and both use PointNet++ [12].

The one you are refering to is the common PSB (Princeton Segmentation Benchmark) dataset [1]. Other Important datasets used for 3D mesh segmentation are:

  1. COSEG [2]
  2. ShapeNet [3]
  3. Other from Princeton [4]
  4. Other basen on subset of ShapeNet [5]

On the other hand, there seems to be no state-of-the-art page for 3D shape segmentation. But the papers I find most important are [6, 7, 8, 9], with 9 the state of the art.


  1. Chen et al: A Benchmark for 3D Mesh Segmentation, 2009
  2. Wang et al: Active co-analysis of a set of shapes, 2012
  3. Kim et al: Learning Part-based Templates from Large Collections of 3D Shapes, 2013
  4. Chang et al: ShapeNet: An Information-Rich 3D Model Repository, 2015
  5. Yi et al: A scalable active framework for region annotation in 3d shape collections, 2016
  6. Kalogerakis et al: Learning 3D Mesh Segmentation and Labeling, 2010
  7. Guo et al: 3D Mesh Labeling via Deep Convolutional Neural Networks, 2015
  8. Kalogerakis et al: 3D Shape Segmentation with Projective Convolutional Networks, 2017
  9. Wang et al: 3D shape segmentation via shape fully convolutional networks, 2018
  10. Wang et al: Associatively Segmenting Instances and Semantics in Point Clouds, 2019
  11. Yang et al: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds, 2019
  12. Qi et al: PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space, 2017

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.