Learning 3D mesh segmentation and labeling

By Evangelos Kalogerakis, Aaron Hertzmann, Karan Singh. 2010

581 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation (2016, methodology): “Along this track, most previous methods [12, 28, 18, 7] employ traditional machine learning techniques and construct classifiers based on geometric features.”
Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts (2015, methodology): “The results are slightly better than [42, 33] and close to those of [24].”
Efficient Human Pose Estimation from Single Depth Images (2013, background): “Kalogerakis et al. [29] classify and segment vertices in a full closed 3D mesh into different parts, but do not deal with occlusions and are sensitive to mesh topology.”
Functional maps (2012, methodology): “Such techniques either pre-segment the shape and try to establish part correspondences, or more recently phrase the segmentation and correspondence (and possibly labelling) in a joint optimization framework [Kalogerakis et al. 2010; Pokrass et al. 2011; Huang et al. 2011] which generally avoids the ”
Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization (2013, methodology): “’s algorithm automatically selects the most informative features from a given set of shape descriptors to train the JointBoost classifier [2].”
Learning Shape Templates With Structured Implicit Functions (2019, background): “Part Segmentation: Others have studied how to decompose mesh collections into consistent sets of semantic parts, either through geometric [14] or learned methods [1, 12, 21, 27].”
Learning part-based templates from large collections of 3D shapes (2013, methodology): “Several existing approaches address the problem of consistent segmentation and labeling by clustering points in an embedded space of local shape features [Kalogerakis et al. 2010; van Kaick et al. 2011a; Huang et al. 2011; Sidi et al. 2011; Hu et al. 2012; Wang et al. 2012].”
PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning (2021, background): “Restricted by the annotations in existing large-scale datasets, previous part-based 3D understanding works mainly focus on identifying parts [15, 30, 26, 55, 32, 58] and part relations [6, 10, 31, 35, 60, 50] for individual 3D objects.”
Probabilistic reasoning for assembly-based 3D modeling (2011, methodology): “Assembly-based 3D modeling can benefit from improved techniques for consistent shape segmentation [Golovinskiy and Funkhouser 2009; Kalogerakis et al. 2010] and for gluing and cutting shapes [Sharf et al.”
GWCNN: A Metric Alignment Layer for Deep Shape Analysis (2017, unknown): “A wide range of fundamental shape analysis problems such as classiﬁcation [BBGO11], segmentation [KHS10], and correspondence [COC14] have been addressed with machine learning techniques (see [XKH ∗ 16] for a survey).”
Convolutional neural networks on surfaces via seamless toric covers (2017, methodology): “All models are manually segmented into eight labels according to the labels in [Kalogerakis et al. 2010].”
Learning 3D Part Detection from Sparsely Labeled Data (2014, methodology): “tives: (1) a k-NN classifier implemented simply as a majority vote of the k = 5 neighbors, and (2) JointBoost [24] which has shown state-of-the-art performance for classifying shape descriptors [13].”