Shape2Pose: human-centric shape analysis
The DOI matches its Crossref record; 58 of the 59 references it cites were found in a registry or an index.
Abstract
As 3D acquisition devices and modeling tools become widely available there is a growing need for automatic algorithms that analyze the semantics and functionality of digitized shapes. Most recent research has focused on analyzing geometric structures of shapes. Our work is motivated by the observation that a majority of man-made shapes are designed to be used by people. Thus, in order to fully understand their semantics, one needs to answer a fundamental question: "how do people interact with these objects?" As an initial step towards this goal, we offer a novel algorithm for automatically predicting a static pose that a person would need to adopt in order to use an object. Specifically, given an input 3D shape, the goal of our analysis is to predict a corresponding human pose, including contact points and kinematic parameters. This is especially challenging for man-made objects that commonly exhibit a lot of variance in their geometric structure. We address this challenge by observing that contact points usually share consistent local geometric features related to the anthropometric properties of corresponding parts and that human body is subject to kinematic constraints and priors. Accordingly, our method effectively combines local region classification and global kinematically-constrained search to successfully predict poses for various objects. We also evaluate our algorithm on six diverse collections of 3D polygonal models (chairs, gym equipment, cockpits, carts, bicycles, and bipedal devices) containing a total of 147 models. Finally, we demonstrate that the poses predicted by our algorithm can be used in several shape analysis problems, such as establishing correspondences between objects, detecting salient regions, finding informative viewpoints, and retrieving functionally-similar shapes.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“TSDF are currently a popular representation for vision-based SLAM in robotics, attracting increasing attention after the seminal work [183].”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [183]
In the citing paper
“Since range cameras carry their own light source, they also work in dark and untextured scenes, which enabled the achievement of remarkable SLAM results [183].”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [183]
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
The Psychology of Everyday Things
Massaro, D. W., & Norman, D. A. (1990) · The American Journal of Psychology · doi:10.2307/1423268 · Cited by 3,466
Data-Driven Grasp Synthesis—A Survey
Bohg, J., Morales, A., Asfour, T., & Kragic, D. (2014) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2289018 · Cited by 929
(2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-79547-6 · Cited by 844
Lee, C. H., Varshney, A., & Jacobs, D. W. (2005) · ACM Transactions on Graphics · doi:10.1145/1073204.1073244 · Cited by 667
Consistent mesh partitioning and skeletonisation using the shape diameter function
Shapira, L., Shamir, A., & Cohen-Or, D. (2008) · The Visual Computer · doi:10.1007/s00371-007-0197-5 · Cited by 542
1Data-Driven Grasp Synthesis- A Survey
Bohg, J., Morales, A., Asfour, T., & Kragić, D. (2014) · MPG.PuRe (Max Planck Society) · Cited by 529
Salient geometric features for partial shape matching and similarity
Gal, R., & Cohen-Or, D. (2006) · ACM Transactions on Graphics · doi:10.1145/1122501.1122507 · Cited by 497
Learning 3D mesh segmentation and labeling
Kalogerakis, E., Hertzmann, A., & Singh, K. (2010) · ACM Transactions on Graphics · doi:10.1145/1778765.1778839 · Cited by 469
A probabilistic model for component-based shape synthesis
Kalogerakis, E., Chaudhuri, S., Koller, D., & Koltun, V. (2012) · ACM Transactions on Graphics · doi:10.1145/2185520.2185551 · Cited by 350
Self-citation
Research works printed but not linked: 1
- Hermans T. Rehg J. M. and Bobick A. 2011. Affordance prediction via learned object attributes. ICRA. Hermans T. Rehg J. M. and Bobick A. 2011. Affordance prediction via learned object attributes. ICRA .
Cited by
Items 101–134 of 134
GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts
Milacski, Z. Á., Niinuma, K., Kawamura, R., la Torre, F. D., & Jeni, L. A. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00404 · Cited by 5
Pose-Guided 3D Human Generation in Indoor Scene
Kim, M., Kang, C., Park, J., & Joo, K. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25195 · Cited by 5
Scene reconstruction and analysis from motion
Kang, C., & Lee, S. (2017) · Graphical Models · doi:10.1016/j.gmod.2017.10.002 · Cited by 5
IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor ScenesPreprint
Li, Q., Mo, K., Yang, Y., Zhao, H., & Guibas, L. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.05298 · Cited by 5
Self-citationPACE: Data-Driven Virtual Agent Interaction in Dense and Cluttered Environments
Mullen, J. F., & Manocha, D. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3247054 · Cited by 4
Keyframe-based multi-contact motion synthesis
Kim, Y., & Lee, S. (2020) · The Visual Computer · doi:10.1007/s00371-020-01956-9 · Cited by 4
iSeg3D: An Interactive 3D Shape Segmentation ToolPreprint
Qian, S., Liu, L., Xu, W., & Lu, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.12988 · Cited by 4
Example-Based Skinning Animation
Mukai, T. (2018) · Springer eBooks · doi:10.1007/978-3-319-14418-4_14 · Cited by 3
Computational design of custom-fit PAP masks
Lu, Y., Wang, Y., Song, P., Wong, H. S., Mok, Y., & Liu, L. (2024) · Computers & Graphics · doi:10.1016/j.cag.2024.103998 · Cited by 3
3D Shape Deformation Using Stick Figures
Seylan, Ç., & Sahillioğlu, Y. (2022) · Computer-Aided Design · doi:10.1016/j.cad.2022.103352 · Cited by 3
CA$^2$T-Net: Category-Agnostic 3D Articulation Transfer from Single ImagePreprint
Collins, J., Liang, A., Malik, J., Zhang, H., & Devernay, F. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.02232 · Cited by 3
3D objects’ shape relevance for saliency measure
Lara, G., de Antonio, A., Negrón, A. P. P., Muñoz, M., & Becerra, E. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-69341-5_22 · Cited by 2
Example-Based Skinning Animation: State of the Art
Mukai, T. (2016) · Springer eBooks · doi:10.1007/978-3-319-30808-1_14-1 · Cited by 2
Three-Dimensional Local Feature Descriptor based on Dynamic Graph Convolution and PointNet
Zhao, B., Wang, Z., Jia, Z., Liang, D., & Liu, Q. (2025) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023-00083 · Cited by 2
Analyzing part functionality via multi-modal latent space embedding and interweaving
Cui, J., Li, S., Hou, F., Hao, A., & Qin, H. (2023) · Computers & Graphics · doi:10.1016/j.cag.2023.06.031 · Cited by 2
3D Articulated Model Retrieval Using Depth Image Input
Lin, J., She, M.-F., Tsai, M., Lin, I., Lau, Y.-C., & Liu, H.-H. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-26756-8_2 · Cited by 2
Estimating Human Pose with both Physical and Physiological Constraints
Su, L., She, J., & Xu, C. (2021) · IEEE International Conference on Industrial Cyber-Physical Systems (ICPS) · doi:10.1109/icps49255.2021.9468181 · Cited by 2
Holden, D. (2017) · ERA · doi:10.2312/diss.20172632000 · Cited by 2
Understanding perceptual mesh \nquality in Virtual Reality and desktop \nsettings
Alfarasani, D. A. (2024) · ORCA Online Research @Cardiff (Cardiff University) · Cited by 2
Pixel-Level Character Motion Style Transfer using Conditional Adversarial Networks
Hu, D., Peng, S., & Liu, X. (2018) · Computer Graphics International · doi:10.1145/3208159.3208161 · Cited by 1
3D indirect shape retrieval based on hand interaction
Irmak, E. C., & Sahillioğlu, Y. (2018) · The Visual Computer · doi:10.1007/s00371-018-1597-4 · Cited by 1
DEEP-LEARNED GENERATIVE REPRESENTATIONS OF 3D SHAPE FAMILIES
Huang, H. (2017) · Scholarworks (University of Massachusetts Amherst) · doi:10.7275/10677221.0 · Cited by 1
Understanding and Exploiting Object Interaction LandscapesPreprint
Pirk, S., Krs, V., Hu, K., Rajasekaran, S. D., Kang, H., Beneš, B., Yoshiyasu, Y., & Guibas, L. J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.08685 · Cited by 1
Self-citationPose-driven generation and optimization of seating furniture
Winkler, A. (2019) · reposiTUm (TU Wien) · doi:10.34726/hss.2019.61400 · Cited by 1
Interactive control of big‐object manipulation animation
Choi, M. G., & Lee, K. H. (2016) · Computer Animation and Virtual Worlds · doi:10.1002/cav.1696
ShapeCreator: 3D Shape Generation from Isomorphic Datasets Based on Autoencoder
Wu, Y., Sun, Z., Song, Y., & Li, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-73600-6_23
Structure-Aware Shape SynthesisPreprint
Balashova, E., Singh, V. K., Wang, J., Teixeira, B., Chen, T., & Funkhouser, T. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.01427
Self-citation3D Functionality Analysis for Shape Modeling via Partial Matching
Guan, Y. (2020) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2020-14050
Learning 3D functionality representations
Hu, R., Savva, M., & van Kaick, O. M. (2020) · SIGGRAPH Asia Courses · doi:10.1145/3415263.3419152
GP-HSI: Human-Scene Interaction with Geometric and Physical Constraints
Li, N., Zhang, G., Du, P., & Lu, D. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3716137
Ergonomics-Driven Computational Design of Furniture and Indoor Layouts
Leimer, K. (2023) · reposiTUm (TU Wien) · doi:10.34726/hss.2023.113961
MOGRAS: Human Motion with Grasping in 3D ScenesPreprint
Bhosikar, K., Katageri, S., Madhavaram, V., Han, K., & Sharma, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.22199
Local Feature Learning for Point Clouds
Guo, Y., Ao, S., Fu, Z., Liu, H. Y., & Hu, Q. (2026) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-95-0648-4_2
3D Scenes Motion Planning and Generation with Motion Diffusion Probabilistic Model
Huang, J., Sun, Y., Xia, G., Liu, Q., & Kankanhalli, M. (2026) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3789508
Metadata
- Authors
- Kim, V. G., Chaudhuri, S., Guibas, L., & Funkhouser, T.
- Affiliations
- Stanford University (US)
- Princeton University (US)
- Venue
- ACM Transactions on Graphics
- Published
- 2014-07-27
- Volume
- 33
- Issue
- 4
- Pages
- 1-12
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W2145429668
- Cited by
- 112
- References
- 59
- Citations by year
- 2026: 2 · 2024: 4 · 2023: 5 · 2022: 5 · 2021: 13 · 2020: 11 · 2019: 11 · 2018: 13 · 2017: 17 · 2016: 20 · 2015: 6 · 2014: 4
- FWCI
- 14.21
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Graphics (publishedVersion)
- Funders
- Division of Information and Intelligent Systems (DMS 1228304, CCF 1161480, IIS-1251217, CNS-0831374)
- Office of Naval Research (N00014-13-1-0341)
- Adobe Systems
- Division of Computer and Network Systems (DMS 1228304, CCF 1161480, IIS-1251217, CNS-0831374)
- Intel Corporation
- Division of Mathematical Sciences (DMS 1228304, CCF 1161480, IIS-1251217, CNS-0831374)
- Air Force Office of Scientific Research (FA9550-12-1-0372)
- Division of Computing and Communication Foundations (DMS 1228304, CCF 1161480, IIS-1251217, CNS-0831374)
- Topics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Processing and 3D Reconstruction
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Keywords
- human pose prediction, 3D shape analysis, object semantics, kinematic constraints, viewpoint selection, shape correspondence, man-made objects
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.