Shape2Pose

By Vladimir G. Kim, Siddhartha Chaudhuri, Leonidas J. Guibas, Thomas A. Funkhouser. 2014

111 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): “These features capture location, curvature, and local context properties of each vertex v and we use the publicly available implementation [13].”
A Field Model for Repairing 3D Shapes (2016, background): “Specifically, the 3D surfaces are missing and/or broken and this phenomenon causes difficulties for many sequential tasks such as 3D object detection and recognition [30, 36], shape analysis [20, 19], and scene understanding [32, 12].”
Phase-functioned neural networks for character control (2017, background): “Lee et al. [2006] conduct rigid shape matching to fit contact-rich motions such as sitting on chairs or lying down on different geometries.”
GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping (2021, unknown): “Pose generation for bodies in 3D scenes: Early methods use either contact annotations [34] or detections [26] on 3D objects, and fit 3D skeletons to these.”
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions (2016, background): “9 shows results on meshes from the Shape2Pose dataset [20].”
Resolving 3D Human Pose Ambiguities With 3D Scene Constraints (2019, background): “Other works like [21, 33] use synthetic 3D scenes and place virtual humans in them to reason about affordances.”
Data-driven structural priors for shape completion (2015, methodology): “Second, the completed point cloud can be used in other geometry analysis tasks that rely on global cues, such as predicting affordances [Kim et al. 2014] and understanding style [Xu et al.”
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration (2020, background): “3DMatch is a RGBD-reconstruction dataset, which consists of 62 real-world indoor scenes collected from existing dataset [54, 47, 55, 32, 54, 11].”
PiGraphs (2016, background): “A notable exception is some recent work for predicting human pose given 3D objects [Kim et al. 2014] and work showing that an explicit model of human presence and object affordances can improve scene synthesis [Fisher et al.”
GRAB: A Dataset of Whole-Body Human Grasping of Objects (2020, methodology): “[30] use synthetic data to learn to detect contact points on a 3D object, and then fit an interacting 3D body skeleton to them.”
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding (2018, background): “Teaching machines to analyze parts is thus essential for many vision, graphics, and robotics applications, such as predicting object functionality [13, 14], human-object interactions [18], shape editing [28, 16], and shape generation [25, 41].”
Meta-representation of shape families (2014, unknown): “Following Kim et al. [2013], our precomputation process interactively grows the state space by suc-”