### Superpixel Algorithms

The below table is __intended to be__ a comprehensive list of superpixel algorithms that have been introduced and used so far. This means that I am doing my best to regularly update this list; however, it is probably impossible to read every paper in every conference, journal or from ArXiv that proposes a new superpixel algorithm or introduced a novel variant of an existing one. Therefore, feel free to point me towards new papers.

This list is supposed to be as comprehensive as possible; however, feel free to point me to papers or implementations in the comments.

For some of the papers, I also provide some reading notes.

Benchmarks | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|

Algorithm | Reference | Impl. | Web | Notes | [] | [] | [] | [] | [] | [] | [] | [] |

W | [], 1992 | C/C++ | Code | ✓ | ✓ | ✓ | ✓ | ✓ | ||||

EAMS | [], 2002 | MatLab/C | Code | ✓ | ✓ | ✓ | ✓ | |||||

NC | [], 2003 | MatLab/C | Code | Notes | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||

FH | [], 2004 | C/C++ | Code | Notes | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||

reFH | —"— | C/C++ | Code | ✓ | ||||||||

RW | [][], 2004 | MatLab/C | Code | ✓ | ||||||||

SL | [], 2008 | ✓ | ✓ | ✓ | ||||||||

QS | [], 2008 | MatLab/C | Code | Notes | ✓ | ✓ | ✓ | ✓ | ✓ | |||

PF | [], 2009 | Java | Code | ✓ | ||||||||

TP | [], 2009 | MatLab/C | Code | Notes | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||

[], 2009 | ||||||||||||

[], 2009 | ||||||||||||

CIS | [], 2010 | C/C++ | Code | Notes | ✓ | ✓ | ✓ | ✓ | ||||

SLIC | [][], 2010 | C/C++ | Code | Notes | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |

vlSLIC | —"— | C/C++ | Code | ✓ | ✓ | ✓ | ||||||

[], 2010 | ||||||||||||

CRS | [][], 2011 | C/C++ | Code | Notes | ✓ | ✓ | ✓ | |||||

ERS | [], 2011 | C/C++ | Code | Notes | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||

PB | [], 2011 | C/C++ | Code | Notes | ✓ | ✓ | ✓ | |||||

[], 2011 | ||||||||||||

[], 2011 | ||||||||||||

DASP | [], 2012 | C/C++ | Code | ✓ | ✓ | |||||||

SEEDS | [], 2012 | C/C++ | Code | Notes | ✓ | ✓ | ||||||

reSEEDS | —"— | C/C++ | Code | ✓ | ✓ | |||||||

TPS | [][], 2012 | MatLab/C | Code | Notes | ✓ | ✓ | ✓ | |||||

VC | [], 2012 | C/C++ | Code | ✓ | ✓ | |||||||

[], 2012 | ||||||||||||

CCS | [][], 2013 | C/C++ | Code | ✓ | ||||||||

VCCS | [], 2013 | C/C++ | Code | ✓ | ✓ | |||||||

[], 2013 | ||||||||||||

[], 2013 | ||||||||||||

[], 2013 | ||||||||||||

[], 2013 | ||||||||||||

CW | [], 2014 | C/C++ | Code | ✓ | ||||||||

ERGC | [][], 2014 | C/C++ | Code | ✓ | ✓ | |||||||

MSS | [], 2014 | C/C++ | — | ✓ | ||||||||

preSLIC | [], 2014 | C/C++ | Code | ✓ | ||||||||

WP | [][], 2014 | Python | Code | ✓ | ✓ | |||||||

LRW | [], 2014 | ✓ | ||||||||||

[], 2014 | ||||||||||||

[], 2014 | ||||||||||||

[], 2014 | ||||||||||||

[], 2014 | ||||||||||||

[], 2014 | Notes | |||||||||||

ETPS | [], 2015 | C/C++ | Code | ✓ | ||||||||

LSC | [], 2015 | C/C++ | Code | ✓ | ✓ | ✓ | ||||||

POISE | [], 2015 | MatLab/C | Code | ✓ | ||||||||

SEAW | [], 2015 | MatLab/C | Code | ✓ | ||||||||

[], 2015 | ||||||||||||

[], 2015 | ||||||||||||

[], 2015 | Notes | |||||||||||

[], 2016 | ||||||||||||

[], 2016 | Notes | |||||||||||

[], 2016 | Notes | |||||||||||

[], 2016 | Notes | |||||||||||

[], 2016 | Notes | |||||||||||

SCALP | [], 2016 | Notes | ✓ | |||||||||

[], 2017 | Notes | |||||||||||

[], 2017 | Notes | |||||||||||

[], 2017 | Notes | |||||||||||

[], 2018 | Code | Notes |

### Benchmarks

There are some benchmarks considering a subset of the above algorithms — including my own Superpixel Benchmark. These papers are listed below; note that the above table of superpixel algorithms also indicates which algorithms are evaluated in the respective papers:

Reference | Comments | Webpage | Notes |
---|---|---|---|

[], 2011 | Evaluates Undersegmentation Error, Boundary Recall and runtime; also evaluates superpixel algorithms as pre-processing task for image segmentation. | ||

[], 2012 | Proposes Corrected Undersegmentation Error; evaluates Undersegmentation Error, Boundary Recall and Robustness against shift, scale, rotation, shear. | Project Page | |

[], 2013 | Evaluates superpixel segmentations in video; propose Motion Undersegmentation Error and Motion Discontinuity Error. | Project Page | |

[], 2012 | Introduces compactness metric (CO); evaluates CO only. | ||

[], 2015 | Evaluates Undersegmentation Error, Boundary Recall and runtime; includes parameter optimization; evaluates on NYUV2 (in 3D, as well); proposes more efficient and improved implementation of SEEDS. | Project Page | |

[], 2016 | Evaluates (Corrected) Undersegmentation Error, Boundary Recall, Explained Variation, Achievable Segmentation Accuracy and runtime; enforces connectivity and includes parameter optimization; also considers maximum/minimum and standard deviation of metrics and deviation from the desired number of superpixels; evaluates robustness against geometric transformations and noise; evaluates on 5 datasets. | Project Page | |

[], 2017 | Introduces regularity metric (RI); evaluates Boundary Recall, - Precision and F1 Measure, Compactness, Undersegmentation Error, Sum-of-Squared Error and Explained Variation and runtime; and provide a code library. | Code | |

[], 2017 | Introduce regularity metric; evaluates regularity only. | Notes |

### References

- [] F. Meyer.
*Color image segmentation.*International Conference on Image Processing and its Applications, 1992, pp. 303-306. - [] D. Comaniciu, P. Meer.
*Mean shift: A robust approach toward feature space analysis.*IEEE Transactions on Pattern Analysis and Machine Intelligence 24 (5) (2002) 603–619. - [] X. Ren, J. Malik.
*Learning a classification model for segmentation.*International Conference on Computer Vision, 2003, pp. 10–17. - [] P. F. Felzenswalb, D. P. Huttenlocher.
*Efficient graph-based image segmentation.*International Journal of Computer Vision 59 (2) (2004) 167–181. - [] L. Grady, G. Funka-Lea.
*Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials.*ECCV Workshops on Computer Vision and Mathematical Methods in Medical and Biomedical Image Analysis, 2004, pp. 230–245. - [] L. Grady.
*Random walks for image segmentation.*IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (11) (2006) 1768–1783. - [] A. Vedaldi, S. Soatto.
*Quick shift and kernel methods for mode seeking.*European Conference on Computer Vision, Vol. 5305, 2008, pp. 705–718. - [] F. Drucker, J. MacCormick.
*Fast superpixels for video analysis.*Workshop on Motion and Video Computing, 2009, pp. 1–8. - [] A. Levinshtein, A. Stere, K. N. Kutulakos, D. J. Fleet, S. J. Dickinson, K. Siddiqi.
*TurboPixels: Fast superpixels using geometric flows.*IEEE Transactions on Pattern Analysis and Machine Intelligence 31 (12) (2009) 2290–2297. - [] O. Veksler, Y. Boykov, P. Mehrani.
*Superpixels and supervoxels in an energy optimization framework.*European Conference on Computer Vision, Vol. 6315, 2010, pp. 211–224. - [] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, S. Susstrunk.
*SLIC superpixels.*Tech. rep., Ecole Polytechnique Federale de Lausanne (2010). - [] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, S. Susstrunk.
*SLIC superpixels compared to state-of-the-art superpixel methods.*IEEE Transactions on Pattern Analysis and Machine Intelligence 34 (11) (2012) 2274–2281. - [] R. Mester, C. Conrad, A. Guevara.
*Multichannel segmentation using contour relaxation: Fast super-pixels and temporal propagation.*Scandinavian Conference Image Analysis, 2011, pp. 250–261. - [] C. Conrad, M. Mertz, R. Mester, Contour-relaxed superpixels.
*Energy Minimization Methods.*Computer Vision and Pattern Recognition, 2013, pp. 280–293. - [] M. Y. Lui, O. Tuzel, S. Ramalingam, R. Chellappa.
*Entropy rate superpixel segmentation.*IEEE Conference on Computer Vision and Pattern Recognition, 2011, pp. 2097–2104. - [] Y. Zhang, R. Hartley, J. Mashford, S. Burn.
*Superpixels via pseudo-boolean optimization.*International Conference on Computer Vision, 2011, pp. 1387–1394. - [] D. Weikersdorfer, D. Gossow, M. Beetz.
*Depth-adaptive superpixels.*International Conference on Pattern Recognition, 2012, pp. 2087–2090. - [] M. van den Bergh, X. Boix, G. Roig, B. de Capitani, L. van Gool.
*SEEDS: Superpixels extracted via energy-driven sampling.*European Conference on Computer Vision, Vol. 7578, 2012, pp. 13–26. - [] D. Tang, H. Fu, X. Cao.
*Topology preserved regular superpixel.*IEEE International Conference on Multimedia and Expo, 2012, pp. 765–768. - [] H. Fu, X. Cao, D. Tang, Y. Han, D. Xu.
*Regularity preserved superpixels and supervoxels.*IEEE Transactions on Multimedia 16 (4) (2014) 1165–1175. - [] J. Wang, X. Wang.
*VCells: Simple and efficient superpixels using edge-weighted centroidal voronoi tessellations.*IEEE Transactions on Pattern Analysis and Machine Intelligence 34 (6)(2012) 1241–1247. - [] H. E. Tasli, C. Cigla, T. Gevers, A. A. Alatan.
*Super pixel extraction via convexity induced boundary adaptation.*IEEE International Conference on Multimedia and Expo, 2013, pp. 1–6. - [] H. E. Tasli, C. Cigla, A. A. Alatan.
*Convexity constrained efficient superpixel and supervoxel extraction.*Signal Processing: Image Communication 33 (2015) 71–85. - [] J. Papon, A. Abramov, M. Schoeler, F. Wörgötter.
*Voxel cloud connectivity segmentation - supervoxels for point clouds.*IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 2027–2034. - [] P. Neubert, P. Protzel.
*Compact watershed and preemptive SLIC: on improving trade-offs of superpixel segmentation algorithms.*International Conference on Pattern Recognition, 2014, pp. 996–1001. - [] P. Buyssens, I. Gardin, S. Ruan.
*Eikonal based region growing for superpixels generation: Application to semi-supervised real time organ segmentation in CT images.*Innovation and Research in BioMedical Engineering 35 (1) (2014) 20–26. - [] P. Buyssens, M. Toutain, A. Elmoataz, O. Lézoray.
*Eikonal-based vertices growing and iterative seeding for efficient graph-based segmentation.*International Conference on Image Processing, 2014, pp. 4368–4372 - [] W. Benesova, M. Kottman.
*Fast superpixel segmentation using morphological processing.*Conference on Machine Vision and Machine Learning, 2014. - [] V. Machairas, E. Decencière, T. Walter.
*Waterpixels: Superpixels based on the watershed transformation.*International Conference on Image Processing, 2014, pp. 4343–4347. - [] V. Machairas, M. Faessel, D. Cardenas-Pena, T. Chabardes, T. Walter, E. Decencière.
*Waterpixels.*Transactions on Image Processing 24 (11) (2015) 3707–3716. - [] J. Yao, M. Boben, S. Fidler, R. Urtasun.
*Real-time coarse-to-fine topologically preserving segmentation.*IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 2947–2955. - [] Z. Li, J. Chen.
*Superpixel segmentation using linear spectral clustering.*IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1356–1363. - [] J. M. R. A. Humayun, F. Li.
*The middle child problem: Revisiting parametric min-cut and seeds for object proposals.*International Conference on Computer Vision, 2015, pp. 1600–1608. - [] J. Strassburg, R. Grzeszick, L. Rothacker, G. A. Fink.
*On the influence of superpixel methods for image parsing.*International Conference on Computer Vision Theory and Application, 2015, pp. 518–527. - [] David Stutz, Alexander Hermans, Bastian Leibe.
*Superpixels: An Evaluation of the State-of-the-Art*. CoRR abs/1612.01601 (2016) - [] David Stutz.
*Superpixel Segmentation: An Evaluation*. GCPR 2015: 555-562 - [] C. Rohkohl, K. Engel,
*Efficient image segmentation using pairwise pixel similarities*, in: DAGM Annual Pattern Recognition Symposium, 2007, pp. 254–263. - [] D. Engel, L. Spinello, R. Triebel, R. Siegwart, H. H. B ̈ulthoff, C. Curio,
*Medial features for superpixel segmentation*, in: IAPR International Conference on Machine Vision Applications, 2009, pp. 248–252. - [] A. Ducournau, S. Rital, A. Bretto, B. Laget,
*Hypergraph coarsening for image superpixelization*, in: International Symposium on I/V Communications and Mobile Network, 2010, pp. 1–4. - [] G. Zeng, P. Wang, J. Wang, R. Gan, H. Zha,
*Structure-sensitive superpixels via geodesic distance*, in: International Conference on Computer Vision, 2011, pp. 447–454. - [] F. Perbet, A. Maki,
*Homogeneous superpixels from random walks*, in: Machine Vision and Applications, Conference on, 2011, pp. 26–30. - [] Y. Du, J. Shen, X. Yu, D. Wang,
*Superpixels using random walker*, in: IEEE Global High Tech Congress on Electronics, 2012, pp. 62–63. - [] J. Yang, Z. Gan, X. Gui, K. Li, C. Hou,
*3-d geometry enhanced superpixels for RGB-D data*, in: Pacific-Rim Conference on Multimedia, 2013, pp. 35–46. - [] J. Zhang, C. Kan, A. G. Schwing, R. Urtasun,
*Estimating the 3d layout of indoor scenes and its clutter from depth sensors*, in: International Conference on Computer Vision, 2013, pp. 1273–1280. - [] Z. Ren, G. Shakhnarovich,
*Image segmentation by cascaded region agglomeration*, in: IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 2011–2018. - [] K.-S. Kim, D. Zhang, M.-C. Kang, S.-J. Ko,
*Improved simple linear iterative clustering superpixels*, in: International Symposium on Consumer Electronics, 2013, pp. 259–260. - [] J. Shen, Y. Du, W. Wang, X. Li,
*Lazy random walks for superpixel segmentation*, Transactions on Image Processing 23 (4) (2014) 1451–1462. - [] P. Morerio, L. Marcenaro, C. S. Regazzoni,
*A generative superpixel method*, in: International Conference on Information Fusion, 2014, pp. 1–7. - [] P. Siva, A. Wong,
*Grid seams: A fast superpixel algorithm for real-time applications*, in: Computer and Robot Vision, Conference on, 2014, pp. 127–134. - [] S. R. S. P. Malladi, S. Ram, J. J. Rodriguez,
*Superpixels using morphology for rock image segmentation*, in: IEEE Southwest Symposium on Image Analysis and Interpretation, 2014, pp. 145–148. - [] O. Freifeld, Y. Li, J. W. Fisher,
*A fast method for inferring high-quality simply-connected superpixels*, in: International Conference on Image Processing, 2015, pp. 2184–2188. - [] J. Lv,
*An improved slic superpixels using reciprocal nearest neighbor clustering*, International Journal of Signal Processing, Image Processing and Pattern Recognition 8 (5) (2015) 239–248. - [] Yong-Jin Liu, Cheng-Chi Yu, Minjing Yu, Ying He.
*Manifold SLIC: A Fast Method to Compute Content-Sensitive Superpixels*. CVPR, pages 651-659, 2016. - [] Alastair Philip Moore, Simon J. D. Prince, Jonathan Warrell, Umar Mohammed, Graham Jones.
*Scene shape priors for superpixel segmentation*. ICCV, pages 771-778, 2009. - [] Yurui Xie, Linfeng Xu, Zhengning Wang.
*Automated co-superpixel generation via graph matching*. Signal, Image and Video Processing 8(4): 753-763, 2014. - [] Se-Ho Lee, Won-Dong Jang, Chang-Su Kim.
*Contour-Constrained Superpixels for Image and Video Processing*. CVPR, pages 5863-5871, 2017. - [] Yinlin Hu, Yunsong Li, Rui Song, Peng Rao, Yangli Wang.
*Minimum barrier superpixel segmentation.*Image and Vision Computing, Volume 70, 2018. - [] Radhakrishna Achanta, Sabine Süsstrunk.
*Superpixels and Polygons Using Simple Non-iterative Clustering*. CVPR, 2017. - [] Imanol Luengo, Mark Basham, Andrew P. French.
*SMURFS: Superpixels from Multi-scale Refinement of Super-regions*. BMVC, 2016. - [] Chun-Rong Huang, Wei-An Wang, Szu-Yu Lin, Yen-Yu Lin.
*USEQ: Ultra-fast superpixel extraction via quantization.*ICPR, 2016. - [] Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis.
*SCALP: Superpixels with Contour Adherence using Linear Path*. ICPR, 2016. - [] Jia-Xin Zhao, Ren Bo, Qibin Hou, Ming-Ming Cheng.
*FLIC: Fast Linear Iterative Clustering with Active Search*. CoRR, 2016. - [] Liuyun Duan, Florent Lafarge.
*Image partitioning into convex polygons*. CVPR, 2015. - [] Y. J. Liu, M. Yu, B. J. Li and Y. He.
*Intrinsic Manifold SLIC: A Simple and Efficient Method for Computing Content-Sensitive Superpixels.*PAMI, 2017. - [] Linfeng Xu, Liaoyuan Zeng, Zhengning Wang.
*Saliency-based superpixels*. Signal, Image and Video Processing, 2014. - [] Jianbing Shen, Xiaopeng Hao, Zhiyuan Liang, Yu Liu, Wenguan Wang, Ling Shao.
*Real-Time Superpixel Segmentation by DBSCAN Clustering Algorithm*. TIP, 2016. - [] A. P. Moore, S. J. D. Prince, J. Warrell, U. Mohammed, and G. Jones.
*Superpixel Lattices*. In Proc. Computer Vision and Pattern Recognition, pages 1–8, 2008. - [] A. Schick, M. Fischer, R. Stiefelhagen,
*Measuring and evaluating the compactness of superpixels*, in: International Conference on Pattern Recognition, 2012, pp. 930–934. - [] P. Neubert, P. Protzel,
*Superpixel benchmark and comparison*, in: Forum Bildverarbeitung, 2012. - [] P. Neubert, P. Protzel, Evaluating superpixels in video.
*Metrics beyond figure-ground segmentation*, in: British Machine Vision Conference, 2013. - [] M. Wang, X. Liu, Y. Gao, X. Ma, N. Q. Soomro.
*Superpixel segmentation: A benchmark*. Sig. Proc.: Image Comm. 56: 28-39, 2017. - [] Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis.
*Robust Shape Regularity Criteria for Superpixel Evaluation*. ICIP, 2017.

What is

your opinionon this article? Did you find it interesting or useful?Let me knowyour thoughts in the comments below or get in touch with me: