Active co-analysis of a set of shapes

By Yunhai Wang, Shmuel Asafi, Oliver Matias van Kaick, Hao Zhang, Daniel Cohen-Or, Baoquan Chen. 2012

276 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

3D Mesh Labeling via Deep Convolutional Neural Networks (2015, background): “We also compare the proposed approach with various other on challenging datasets [Wang et al. 2012], as shown in Figure 16.”
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].”
Data-driven structural priors for shape completion (2015, unknown): “2012], 37 tables from ShapeNet, 287 chairs from COSEG dataset [Wang et al. 2012].”
Learning Shape Abstractions by Assembling Volumetric Primitives (2016, background): “By virtue of these properties, our representation can enable several applications related to shape similarity, part discovery, perception and shape manipulation.”
3D Shape Segmentation with Projective Convolutional Networks (2016, methodology): “As the authors of the PSB benchmark note [50], many 3D models cannot be re-meshed or re-constructed due to mesh degeneracies, hence they were not included in their datasets.”
MeshCNN: a network with an edge (2019, methodology): “We used the COSEG [2012] dataset which provides ground truth segmentation as a label per face.”
3D Shape Segmentation and Labeling via Extreme Learning Machine (2014, unknown): “Wang et al. [WAvK ∗ 12] introduced active learning for interactive labeling large model sets.”
Interactive shape co-segmentation via label propagation (2014, result): “The experimental results demonstrate the effectiveness of our approach.”
Shape Completion from a Single RGBD Image (2017, methodology): “Moreover, if the models in M are already segmented to parts [30], we further re ne the alignment in a global-to-local manner [21], and compose the best aligned parts together to calculate the initial guess.”
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding (2018, methodology): “Shape co-segmentation benchmarks [38, 11] were proposed to study co-segmentation among similar shapes.”
Multi-View Intact Space Learning (2015, methodology): “D model provided by [53], we extracted the point cloud data X (i.e., point positions in rectangular space coordinates), and then projected it into three 2-”