Joint shape segmentation with linear programming

By Qi-Xing Huang, Vladlen Koltun, Leonidas J. Guibas. 2011

197 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

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

Citations in the corpus

3D shape segmentation via shape fully convolutional networks (2017, methodology): “34 The segmentation shape of matching shape is then established 35 to realize the joint segmentation [39, 34] of 3D shapes.”
NASA: Neural Articulated Shape Approximation (2019, background): “A further core challenge, and subject of continuing research, is the automatic creation of this partbased representation [1, 7, 12].”
Interactive shape co-segmentation via label propagation (2014, methodology): “[13] introduce an optimization strategy for simultaneously optimizing the saliency of each segmentation as well as consistency between segmentations.”
Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization (2013, methodology): “We also compared to the unsupervised algorithm [6] on the Princeton Segmentation Benchmark.”
Learning 3D Part Detection from Sparsely Labeled Data (2014, background): “The problem of mesh labeling has largely been approached via segmentation (see [20], [8], [10], [22]).”
Creating consistent scene graphs using a probabilistic grammar (2014, methodology): “Significant progress has been made in the areas of joint shape segmentation [Golovinskiy and Funkhouser 2009; Huang et al. 2011; Sidi et al. 2011; Hu et al. 2012; Zheng et al. 2014] and joint shape matching [Nguyen et al.”
3D Shape Segmentation and Labeling via Extreme Learning Machine (2014, unknown): “To accelerate the computation, these methods often cluster super-faces [HKG11,WAvK ∗ 12] † Corresponding author: kaixu@nudt.edu.cn obtained via over-segmentation.”
Deformation-driven shape correspondence via shape recognition (2017, methodology): “2011], unsupervised co-analysis [Huang et al. 2011; Kim et al. 2013; Xu et al. 2010, 2012; Zheng et al. 2014] or implied by contexts [Laga et al.”
Data-driven structural priors for shape completion (2015, methodology): “Several methods have been developed for detecting part structure of unlabeled shapes without any supervision [Golovinskiy and Funkhouser 2009; Sidi et al. 2011; Hu et al. 2012; Huang et al. 2011; Huang et al. 2014] or with some user input [Kalogerakis et al.”
3D Mesh Labeling via Deep Convolutional Neural Networks (2015, methodology): “To address this problem, several cosegmentation approaches [Huang et al. 2011; Sidi et al. 2011; Hu et al. 2012; van Kaick et al. 2013; Kim et al. 2013] were proposed, which aimed to extract common geometric subsets and their correspondence from each category of 3D shapes.”
Shape2Pose (2014, background): “2013], consistent segmentations [Golovinskiy and Funkhouser 2009; Huang et al. 2011; Sidi et al. 2011], region classification [Kalogerakis et al.”
A scalable active framework for region annotation in 3D shape collections (2016, background): “While earlier approaches segmented individual shapes [Shamir 2008], several recent works have shown that joint analysis of a group of related objects provides better geometric cues for what constitutes a semantically meaningful part [Sidi et al. 2011; Huang et al. 2011; Hu et al. 2012; Huang et al. ”
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 ”
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.”
3D Shape Segmentation with Projective Convolutional Networks (2016, methodology): “Other approaches segment shapes by employing non-rigid alignment steps through deformable part templates [27, 20], or transfer labels through surface correspondences and functional maps between 3D shapes [48, 22, 50, 27, 23].”