Dictionaries are very useful objects for data analysis, as they enable a compact representation of large sets of objects through the combination of atoms. Dictionary-based techniques have also particularly benefited from the recent advances in machine learning, which has allowed for data-driven algorithms to take advantage of the redundancy in the input dataset and discover relations between objects without human supervision or hard-coded rules. Despite the success of dictionary-based techniques on a wide range of tasks in geometric modeling and geometry processing, the literature is missing a principled state-of-the-art of the current knowledge in this field. To fill this gap, we provide in this survey an overview of data-driven dictionary-based methods in geometric modeling. We structure our discussion by application domain: surface reconstruction, compression, and synthesis. Contrary to previous surveys, we place special emphasis on dictionary-based methods suitable for 3D data synthesis, with applications in geometric modeling and design. Our ultimate goal is to enlight the fact that these techniques can be used to combine the data-driven paradigm with design intent to synthesize new plausible objects with minimal human intervention. This is the main motivation to restrict the scope of the present survey to techniques handling point clouds and meshes, making use of dictionaries whose definition depends on the input data, and enabling shape reconstruction or synthesis through the combination of atoms.
Point set surfaces.
In Proceedings of the Conference on Visualization '01 (Washington, DC, USA, 2001), VIS '01, pp. 21–28.
Progressive compression for lossless transmission of triangle meshes.
In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques (New York, NY, USA, 2001), SIGGRAPH '01, pp. 195–202.
K-svd: An algorithm for designing overcomplete dictionaries for sparse representation.
IEEE Transactions on Signal Processing 54, 11 (Nov 2006), 4311–4322.
Shapesynth: Parameterizing model collections for coupled shape exploration and synthesis.
Computer Graphics Forum (Special issue of Eurographics 2014) (2014).
Representing animations by principal components.
Computer Graphics Forum 19, 3 (2000), 411–418.
Seeing 3d chairs: exemplar part-based 2d-3d alignment using a large dataset of cad models.
In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014), pp. 3762–3769.
Shape Google: Geometric words and expressions for invariant shape retrieval.
ACM Transactions on Graphics 30 (2011), 1:1–1:20.
A non-local algorithm for image denoising.
In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02 (Washington, DC, USA, 2005), CVPR '05, pp. 60–65.
Learning deep architectures for ai.
Found. Trends Mach. Learn. 2, 1 (2009), 1–127.
Deep learning for shape analysis.
In Proceedings of Eurographics Tutorials (2016), EG '16, pp. 2:1–2:1.
Matching with shape contexts.
In 2000 Proceedings Workshop on Content-based Access of Image and Video Libraries (2000), pp. 20–26.
Distributed optimization and statistical learning via the alternating direction method of multipliers.
Foundations and Trends in Machine Learning 3, 1 (2011), 1–122.
Machine Learning 45, 1 (2001), 5–32.
Astronomical Image Denoising Using Dictionary Learning.
Astronomy and Astrophysics - A&A 556, A132 (2013), 14 pp.
A morphable model for the synthesis of 3d faces.
In Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques (New York, NY, USA, 1999), SIGGRAPH '99, pp. 187–194.
Fast approximate energy minimization via graph cuts.
IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 11 (2001), 1222–1239.
Network dissection: Quantifying interpretability of deep visual representations.
In Computer Vision and Pattern Recognition (2017).
ShapeNet: An Information-Rich 3D Model Repository.
Tech. Rep. arXiv:1512.03012 [cs.GR], Stanford University – Princeton University – Toyota Technological Institute at Chicago, 2015.
Data-driven suggestions for creativity support in 3d modeling.
ACM Transactions on Graphics (Proc. Siggraph Asia) 29, 6 (Dec. 2010), 183:1–183:10.
Probabilistic reasoning for assembly-based 3D modeling.
ACM Transactions on Graphics (Proc. Siggraph) 30, 4 (2011), 35:1–35:10.
A simple geometric model for elastic deformations.
ACM Transactions on Graphics (Proc. Siggraph) 29, 4 (2010), 38:1–38:6.
Advances in knowledge discovery and data mining.
Menlo Park, CA, USA, 1996, ch. Bayesian Classification (AutoClass): Theory and Results, pp. 153–180.
Self-similarity for accurate compression of point sampled surfaces.
Computer Graphics Forum 33, 2 (2014), 155–164.
Model globally, match locally: Efficient and robust 3d object recognition.
In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (June 2010), pp. 998–1005.
Image denoising via sparse and redundant representations over learned dictionaries.
IEEE Transactions on Image Processing 15, 12 (Dec 2006), 3736–3745.
Method of optimal directions for frame design.
In 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258) (1999), vol. 5, pp. 2443–2446 vol.5.
Sparse and redundant representations, from theory to applications in signal and image processing.
New York, NY, USA, 2010.
Sketch-based shape retrieval.
ACM Transactions on Graphics (Proc. Siggraph) 31, 4 (2012), 31:1–31:10.
Photosketcher: interactive sketch-based image synthesis.
IEEE Computer Graphics and Applications (2011), 56–66.
Family of iterative ls-based dictionary learning algorithms, ils-dla, for sparse signal representation.
Digital Signal Processing 17, 1 (2007), 32 – 49.
Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography.
Commun. ACM 24, 6 (1981), 381–395.
Example-driven deformations based on discrete shells.
Computer Graphics Forum 30, 8 (2011), 2246–2257.
Modeling by example.
In ACM Transactions on Graphics (Proc. Siggraph) (New York, NY, USA, 2004), SIGGRAPH '04, pp. 652–663.
A point set generation network for 3d object reconstruction from a single image.
CoRR abs/1612.00603 (2016).
Data-driven shape interpolation and morphing editing.
Computer Graphics Forum (2016).
Sparse representation of terrains for procedural modeling.
Computer Graphics Forum (Proc Eurographics) 35, 2 (2016), 177–187.
Algebraic point set surfaces.
In ACM Transactions on Graphics (Proc. Siggraph) (New York, NY, USA, 2007), SIGGRAPH '07.
ACM Trans. Graph. 21, 3 (July 2002), 355–361.
In Proceedings of the 2003 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (Aire-la-Ville, Switzerland, Switzerland, 2003), SCA '03, Eurographics Association, pp. 62–67.
Sur l'approximation, par éléments finis d'ordre un, et la résolution, par pénalisation-dualité, d'une classe de problèmes de Dirichlet non linéaires.
Revue Française d'Automatique, Informatique, Recherche Opérationnelle. Série Rouge 9, 2 (1975), 41–76.
A dual algorithm for the solution of nonlinear variational problems via finite element approximation.
Computers & Mathematics with Applications 2, 1 (1976), 17 – 40.
Generative adversarial networks.
ArXiv e-prints (June 2014).
Pose-oblivious shape signature.
IEEE Transactions on Visualization & Computer Graphics Issue No. 02 - March/April (2007 vol. 13) (March 2007), 261–271.
3d mesh labeling via deep convolutional neural networks.
ACM Transactions on Graphics 35, 1 (2015), 3:1–3:12.
Self-similarity based compression of point set surfaces with application to ray tracing.
Computers & Graphics 32, 2 (2008), 221 – 234.
Exploring the geometry of the space of shells.
Comput. Graph. Forum 33, 5 (Aug. 2014), 247–256.
Functional map networks for analyzing and exploring large shape collections.
ACM Transactions on Graphics (Proc. Siggraph) 33, 4 (2014), 36:1–36:11.
Sparse localized decomposition of deformation gradients.
Computer Graphics Forum 33, 7 (Oct. 2014), 239–248.
Hierarchical detail enhancing mesh-based shape generation with 3d generative adversarial network.
CoRR abs/1709.07581 (2017).
A probabilistic model for component-based shape synthesis.
ACM Transactions on Graphics 31, 4 (July 2012), 55:1–55:11.
Probabilistic Graphical Models : Principles and Techniques.
Compression of soft-body animation sequences.
Computers & Graphics 28, 1 (2004), 25 – 34.
Screened poisson surface reconstruction.
ACM Trans. Graph. 32, 3 (July 2013), 29:1–29:13.
Model composition from interchangeable components.
In Proceedings of the 15th Pacific Conference on Computer Graphics and Applications (Washington, DC, USA, 2007), PG '07, pp. 129–138.
Exploring Collections of 3D Models using Fuzzy Correspondences.
ACM Transactions on Graphics (Proc. Siggraph) 31, 4 (2012).
Learning part-based templates from large collections of 3D shapes.
ACM Transactions on Graphics (Proc. Siggraph) 32, 4 (jul 2013).
Acquiring 3d indoor environments with variability and repetition.
ACM Transactions on Graphics (Proc. Siggraph Asia) 31, 6 (2012), 138:1–138:11.
Imagenet classification with deep convolutional neural networks.
In Advances in Neural Information Processing Systems 25. 2012, pp. 1097–1105.
Statistical geometry representation for efficient transmission and rendering.
ACM Transactions on Graphics 24, 2 (Apr. 2005), 348–373.
Auto-encoding variational bayes.
ArXiv e-prints (Dec. 2013).
Bag of words and local spectral descriptor for 3d partial shape retrieval.
In Proceedings of the 4th Eurographics Conference on 3D Object Retrieval (Aire-la-Ville, Switzerland, Switzerland, 2011), 3DOR '11, pp. 41–48.
Gradient-based learning applied to document recognition.
2278 – 2324.
Compression of 3d mesh sequences by temporal segmentation.
Computer Animation and Virtual Worlds 24, 3-4 (2013), 365–375.
Database-assisted object retrieval for real-time 3d reconstruction.
Computer Graphics Forum 34, 2 (2015), 435–446.
3d shape reconstruction from sketches via multi-view convolutional networks.
CoRR abs/1707.06375 (2017).
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations.
In Proceedings of the 26th Annual International Conference on Machine Learning (2009), ICML '09, pp. 609–616.
Linear rotation-invariant coordinates for meshes.
In ACM Transactions on Graphics (Proc. Siggraph) (2005), pp. 479–487.
Autoencoding beyond pixels using a learned similarity metric.
In Proceedings of the 33nd International Conference on Machine Learning, ICML (2016), pp. 1558–1566.
Grass: Generative recursive autoencoders for shape structures.
ACM Trans. Graph. 36, 4 (July 2017), 52:1–52:14.
Sparse coding for machine learning, image processing and computer vision.
Thèses, École normale supérieure de Cachan - ENS Cachan, Nov. 2010.
Online learning for matrix factorization and sparse coding.
Journal of Machine Learning Research 11 (Mar. 2010), 19–60.
Partial and approximate symmetry detection for 3d geometry.
ACM Trans. Graph. 25, 3 (July 2006), 560–568.
Meshless deformations based on shape matching.
In ACM Transactions on Graphics (Proc. Siggraph) (New York, NY, USA, 2005), SIGGRAPH '05, pp. 471–478.
3d mesh compression: Survey, comparisons, and emerging trends.
ACM Computing Surveys 47, 3 (2015), 44:1–44:41.
Symmetry in 3d geometry: Extraction and applications.
Comput. Graph. Forum 32, 6 (Sept. 2013), 1–23.
Learning multiscale sparse representations for image and video restoration.
Multiscale Modeling & Simulation 7, 1 (2008), 214–241.
Structure-aware shape processing.
In SIGGRAPH Asia 2013 Courses (New York, NY, USA, 2013), SA '13, ACM, pp. 1:1–1:20.
Sparse localized deformation components.
ACM Transactions on Graphics (Proc. Siggraph Asia) 32, 6 (2013), 179:1–179:10.
The shape variational autoencoder: A deep generative model of part-segmented 3d objects.
Computer Graphics Forum 36, 5 (2017), 1–12.
A search-classify approach for cluttered indoor scene understanding.
ACM Transactions on Graphics (Proc. Siggraph Asia) 31, 6 (2012), 137:1–137:10.
Real-time 3d reconstruction at scale using voxel hashing.
ACM Transactions on Graphics (Proc. Siggraph Asia) 32, 6 (Nov. 2013), 169:1–169:11.
Emergence of simple-cell receptive field properties by learning a sparse code for natural images.
Nature 381 (07 1996), 607–9.
Feature Preserving Point Set Surfaces based on Non-Linear Kernel Regression.
Computer Graphics Forum (2009).
Exploration of continuous variability in collections of 3d shapes.
ACM Transactions on Graphics (Proc. Siggraph) 30, 4 (2011), 33:1–33:10.
Lzma sdk version 16.04.
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference.
San Francisco, CA, USA, 1988.
Sparse Modeling of Textures.
Journal of Mathematical Imaging and Vision 34, 1 (May 2009), 17–31.
The Algorithmic Beauty of Plants.
New York, NY, USA, 1990.
Example-based 3d scan completion.
In Proceedings of the Third Eurographics Symposium on Geometry Processing (Aire-la-Ville, Switzerland, Switzerland, 2005), SGP '05.
Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition.
In Proceedings of 27th Asilomar Conference on Signals, Systems and Computers (Nov 1993), pp. 40–44 vol.1.
Pointnet: Deep learning on point sets for 3d classification and segmentation.
Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) (2017).
Dictionaries for sparse representation modeling.
Proceedings of the IEEE 98, 6 (June 2010), 1045–1057.
Critical points of an autoencoder can provably recover sparsely used overcomplete dictionaries.
CoRR abs/1708.03735 (2017).
Double sparsity: Learning sparse dictionaries for sparse signal approximation.
IEEE Transactions on Signal Processing 58, 3 (March 2010), 1553–1564.
Snappaste: an interactive technique for easy mesh composition.
The Visual Computer 22, 9 (Sep 2006), 835–844.
Estimating the dimension of a model.
The Annals of Statistics 6, 2 (03 1978), 461–464.
Structure recovery by part assembly.
ACM Transactions on Graphics (Proc. Siggraph Asia) 31, 6 (2012), 180:1–180:11.
Data-driven structural priors for shape completion.
ACM Transactions on Graphics (Proc. Siggraph Asia) 34, 6 (Oct. 2015).
Fast vector quantization for efficient rendering of compressed point-clouds.
Computers and Graphics 32, 2 (Apr. 2008), 246–259.
Slam++: Simultaneous localisation and mapping at the level of objects.
In Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition (Washington, DC, USA, 2013), CVPR '13, pp. 1352–1359.
Body talk: Crowdshaping realistic 3d avatars with words.
ACM Transactions on Graphics (Proc. Siggraph) 35, 4 (2016), 54:1–54:14.
Simple and efficient compression of animation sequences.
In Proceedings of the 2005 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (New York, NY, USA, 2005), SCA '05, pp. 209–217.
How to train your deep neural network with dictionary learning.
CoRR abs/1612.07454 (2016).
Surfnet: Generating 3d shape surfaces using deep residual networks.
CoRR abs/1703.04079 (2017).
An interactive approach to semantic modeling of indoor scenes with an rgbd camera.
ACM Transactions on Graphics (Proc. Siggraph Asia) 31, 6 (2012), 136:1–136:11.
Very deep convolutional networks for large-scale image recognition.
CoRR abs/1409.1556 (2014).
Mesh-based inverse kinematics.
ACM transactions on graphics 24, 3 (2005), 488–495.
Variational Texture Synthesis with Sparsity and Spectrum Constraints.
Journal of Mathematical Imaging and Vision 52, 1 (2015), 124–144.
On the computational intractability of exact and approximate dictionary learning.
IEEE Signal Processing Letters 22, 1 (Jan 2015), 45–49.
Sharing visual features for multiclass and multiview object detection.
IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 5 (2007), 854–869.
Deep dictionary learning.
IEEE Access 4 (2016), 10096–10109.
Learning design patterns with bayesian grammar induction.
In Proceedings of the 25th Annual ACM Symposium on User Interface Software and Technology (New York, NY, USA, 2012), UIST '12, pp. 63–74.
On the complexity of nonnegative matrix factorization.
SIAM J. on Optimization 20, 3 (2009), 1364–1377.
Part-based modelling of compound scenes from images.
In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2015), pp. 878–886.
Coddyac: Connectivity driven dynamic mesh compression.
In 2007 3DTV Conference (May 2007), pp. 1–4.
Cobra: Compression of the basis for pca represented animations.
Computer Graphics Forum 28, 6 (2009), 1529–1540.
Geometry-driven local neighbourhood based predictors for dynamic mesh compression.
Computer Graphics Forum 29, 6 (2010), 1921–1933.
A perception correlated comparison method for dynamic meshes.
IEEE Transactions on Visualization and Computer Graphics 17, 2 (Feb 2011), 220–230.
Real-time nonlinear shape interpolation.
ACM Transactions on Graphics 34, 3 (2015), 34:1–34:10.
Fast and reliable example-based mesh ik for stylized deformations.
ACM Transactions on Graphics (Proc. Siggraph Asia) 35, 6 (Nov. 2016), 235:1–235:12.
Multi-scale geometry interpolation.
Computer Graphics Forum 29, 2 (2010), 309–318.
O-cnn: Octree-based convolutional neural networks for 3d shape analysis.
ACM Transactions on Graphics (SIGGRAPH) 36, 4 (2017).
Articulated-motion-aware sparse localized decomposition.
Computer Graphics Forum (2016), n/a–n/a.
3d shapenets: A deep representation for volumetric shapes.
In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2015), pp. 1912–1920.
Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling.
CoRR abs/1610.07584 (2016).
Image meshing via hierarchical optimization.
Frontiers of Information Technology & Electronic Engineering 17, 1 (2016), 32–40.
Data-driven shape analysis and processing.
CoRR abs/1502.06686 (2015).
Transductive 3d shape segmentation using sparse reconstruction.
Computer Graphics Forum 33, 5 (2014), 107–115.
Surface approximation via sparse representation and parameterization optimization.
Computer Aided Design 78, C (2016), 179–187.
Survey on sparsity in geometric modeling and processing.
Graphical Models 82 (2015), 160 – 180.
3d shape segmentation and labeling via extreme learning machine.
Computer Graphics Forum 33, 5 (2014), 85–95.
Sketch-to-design: Context-based part assembly.
Computer Graphics Forum (2013).
Fit and diverse: Set evolution for inspiring 3d shape galleries.
ACM Transactions on Graphics (Proc. Siggraph) 31, 4 (2012), 57:1–57:10.
Poisson shape interpolation.
In Proceedings of the 2005 ACM Symposium on Solid and Physical Modeling (New York, NY, USA, 2005), SPM '05, pp. 267–274.
Robust surface reconstruction via dictionary learning.
ACM Transactions on Graphics (Proc. Siggraph Asia) 33 (2014).
Co-constrained handles for deformation in shape collections.
ACM Transactions on Graphics (Proc. Siggraph Asia) 33, 6 (2014), 187:1–187:11.
Geometry representations with unsupervised feature learning.
vol. 00, pp. 137–142.