Deep Learning for Robust Normal Estimation in Unstructured Point Clouds

Computer Graphics Forum

Volumn 35, Issue 5, 2016, Pages 281-290

  Boulch, Alexandre ^a   Marlet, Renaud ^b  

^a ONERA   (France)

^b UNIVERSITÉ PARIS EST   (France)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS;

GROUND TRUTH DATA; NORMAL DIRECTION; NORMAL ESTIMATION; SAMPLING DENSITIES; SCENE UNDERSTANDING; SHARP FEATURES; STATE OF THE ART; UNSTRUCTURED POINT CLOUDS;

ESTIMATION;

EID: 84982124657     PISSN: 01677055     EISSN: 14678659     Source Type: Journal    
DOI: 10.1111/cgf.12983     Document Type: Article

References (50)

1. Alexa M., Behr J., Cohen-Or D., Fleishman S., Levin D., Silva C.T.: Computing and rendering point set surfaces. IEEE Tr. on Visualization and Computer Graphics 9, 1 (2003), 3–15. 1
2. Alliez P., Cohen-Steiner D., Tong Y., Desbrun M.: Voronoi-based variational reconstruction of unoriented point sets. In SGP (2007), pp. 39–48. 1
3. Avron H., Sharf A., Greif C., Cohen-Or D.: Lisparse reconstruction of sharp point set surfaces. TOG 29, 5 (2010), 135: 1–135:12. 1
4. Ballard D.H.: Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognition 13, 2 (1981), 111–122. 2
5. Boulch A., De LA GORCE M., Marlet R.: Piecewiseplanar 3D reconstruction with edge and corner regularization. CGF 33, 5 (2014), 55–64. 1
6. Borrmann D., Elseberg J., Lingemann K., Nüchter A.: The 3D Hough Transform for plane detection in point clouds: A review and a new accumulator design. 3D Research 2, 2 (2011). 2, 3
7. Boulch A., Marlet R.: Fast and robust normal estimation for point clouds with sharp features. CGF 31, 5 (2012), 1765–1774. 1, 2, 3, 4, 5, 6, 7, 8, 9
8. Bansal A., Russell B., Gupta A.: Marr revisited: 2D-3D alignment via surface normal prediction. In CVPR (2016). 2
9. Chauve A.-L., Labatut P., Pons J.-P.: Robust piecewiseplanar 3D reconstruction and completion from large-scale unstructured point data. In CVPR (2010), pp. 1261–1268. 1
10. Cazals F., Pouget M.: Estimating differential quantities using polynomial fitting of osculating jets. Computer Aided Geometric Design 22, 2 (2005), 121–146. 1, 6, 9
11. Davies E.R.: Application of the generalised Hough transform to corner detection. Computers and Digital Techniques, IEE Proceedings E 135, 1 (1988), 49–54. 2
12. IEEE GRSS Data Fusion Contest, 2015. URL: http://www.grss-ieee.org/community/technical-committees/data-fusion. 5
13. Dey T.K., Goswami S.: Provable surface reconstruction from noisy samples. In SoCG (2004), pp. 330–339. 1, 5, 6, 9
14. Duda R.O., Hart P.E.: Use of the Hough transformation to detect lines and curves in pictures. Comm. ACM 15, 1 (1972), 11–15. 2
15. Ferri F., Gianni M., Menna M., Pirri F.: Point cloud segmentation and 3D path planning for tracked vehicles in cluttered and dynamic environments. In 3rd IROS Workshop on Robots in Clutter: Perception and Interaction in Clutter (2014). 1
16. Girshick R., Donahue J., Darrell T., Malik J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR (2014), pp. 580–587. 2
17. Guennebaud G., Gross M.: Algebraic point set surfaces. TOG 26, 3 (2007), 23. 1
18. Graham B.: Sparse 3D convolutional neural networks. In BMVC (2015). 2
19. Hoppe H., DeRose T., Duchamp T., McDonald J., Stuetzle W.: Surface reconstruction from unorganized points. ACM SIGGRAPH Computer Graphics 26, 2 (1992), 71–78. 1, 6, 7, 9
20. Huang H., Li D., Zhang H., Ascher U., Cohen-Or D.: Consolidation of unorganized point clouds for surface reconstruction. TOG 28, 5 (2009), 176. 1
21. Hough P. V. C.: Method and means for recognizing complex patterns. U.S. Patent 3.069.654 (1962). 2
22. Hinton G.E., Srivastava N., Krizhevsky A., Sutskever I., Salakhutdinov R.R.: Improving neural networks by preventing co-adaptation of feature detectors. preprint arXiv:1207.0580 (2012). 2
23. Illingworth J., Kittler J.: A survey of the Hough transform. CVGIP 44, 1 (1988), 87–116. 2
24. Jeong W.K., Ivrissimtzis I.P., Seidel H.P.: Neural meshes: statistical learning based on normals. In Pacific Conference on Computer Graphics & Applications (CGA) (2003), pp. 404–408. 2
25. Kiryati N., Eldar Y., Bruckstein A.M.: A probabilistic Hough transform. Pattern Recognition 24, 4 (1991), 303–316. 2
26. Knopp J., Prasad M., Willems g., Timofte R., Van Gool L.: Hough transform and 3D SURF for robust three dimensional classification. In ECCV (2010), pp. 589–602. 2
27. Krizhevsky A., Sutskever I., Hinton G.E.: Imagenet classification with deep convolutional neural networks. In NIPS (2012). 2
28. LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D.: Backpropagation applied to handwritten zip code recognition. Neural computation 1, 4 (1989), 541–551. 2, 4
29. Li B., Shen C., Dai Y., van den Hengel A., He M.: Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs. In CVPR (2015), pp. 1119–1127. 2
30. Long J., Shelhamer E., Darrell T.: Fully convolutional networks for semantic segmentation. In CVPR (2015). 2
31. Li B., Schnabel R., Klein R., Cheng Z., Dang g., Jin S.: Robust normal estimation for point clouds with sharp features. Computers & Graphics 34, 2 (2010), 94–106. 1, 4, 6, 7, 9
32. Liu X., Zhang J., Cao J., Li B., Liu L.: Quality point cloud normal estimation by guided least squares representation. Computers & Graphics 51, C (2015), 106–116. 1, 4, 6, 7, 9
33. Mitra N.J., Nguyen A., Guibas L.: Estimating surface normals in noisy point cloud data. International Journal of Computational Geometry & Applications 14, 04n05 (2004), 261–276. 1
34. Öztireli A. C., Guennebaud G., Gross M.H.: Feature preserving point set surfaces based on non-linear kernel regression. CGF 28, 2 (2009), 493–501. 1
35. Penedones H., Collobert R., Fleuret F., Grangier D.: Improving Object Classification using Pose Information. Research report Idiap-RR-30-2012, Idiap Research Institute, 2012. 2
36. Pauly M., Keiser R., Kobbelt L.P., Gross M.: Shape modeling with point-sampled geometry. TOG 22, 3 (2003), 641–650. 1
37. Pham M.-T., Woodford O.J., Perbet F., Maki A., Stenger B., Cipolla R.: A new distance for scale-invariant 3D shape recognition and registration. In ICCV (2011), pp. 145–152. 2
38. Rusinkiewicz S., Levoy M.: QSplat: a multiresolution point rendering system for large meshes. In SIGGRAPH (New York, NY, USA, 2000), pp. 343–352. 1
39. Sermanet P., Eigen D., Zhang X., Mathieu M., Fergus R., LeCun Y.: Overfeat: Integrated recognition, localization and detection using convolutional networks. In ICLR (2014). 2
40. Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V., Rabinovich A.: Going deeper with convolutions. In CVPR (2014). 2
41. Sun Y., Schaefer S., Wang W.: Denoising point sets via l0 minimization. CAGD 35–36 (2015), 2–15. 1
42. Shen F., Wang H.: Corner detection based on modified Hough transform. Pattern Recognition Letters 23, 8 (2002), 1039–1049. 2
43. Schnabel R., Wahl R., Klein R.: Efficient RANSAC for point-cloud shape detection. CGF 26, 2 (2007), 214–226. 1
44. Tsuji S., Matsumoto F.: Detection of ellipses by a modified Hough transformation. IEEE Trans. on Computers 27, 8 (1978). 2
45. Wang X., Fouhey D.F., Gupta A.: Designing deep networks for surface normal estimation. In CVPR (2015), pp. 539–547. 2
46. Wu Z., Song S., Khosla A., Yu F., Zhang L., Tang X., Xiao J.: 3D ShapeNets: A deep representation for volumetric shape modeling. In CVPR (2015). 2
47. Xu L., Oja E.: Randomized Hough transform (RHT): basic mechanisms, algorithms, and computational complexities. CVGIP: Image understanding 57, 2 (1993), 131–154. 2
48. Zhang J., Cao J., Liu X., Wang J., Liu J., Shi X.: Point cloud normal estimation via low-rank subspace clustering. Computers & Graphics 37, 6 (2013), 697–706. 1, 7, 9
49. Zeiler M.D., Fergus R.: Visualizing and understanding convolutional networks. In ECCV (2014), pp. 818–833. 2
50. Zwicker M., Pfister H., Van Baar J., Gross M.: Surface splatting. In SIGGRAPH (2001), ACM, pp. 371–378. 1