Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

AdaContour: Adaptive Contour Descriptor with Hierarchical Representation (2404.08292v1)

Published 12 Apr 2024 in cs.CV and cs.GR

Abstract: Existing angle-based contour descriptors suffer from lossy representation for non-starconvex shapes. By and large, this is the result of the shape being registered with a single global inner center and a set of radii corresponding to a polar coordinate parameterization. In this paper, we propose AdaContour, an adaptive contour descriptor that uses multiple local representations to desirably characterize complex shapes. After hierarchically encoding object shapes in a training set and constructing a contour matrix of all subdivided regions, we compute a robust low-rank robust subspace and approximate each local contour by linearly combining the shared basis vectors to represent an object. Experiments show that AdaContour is able to represent shapes more accurately and robustly than other descriptors while retaining effectiveness. We validate AdaContour by integrating it into off-the-shelf detectors to enable instance segmentation which demonstrates faithful performance. The code is available at https://github.com/tding1/AdaContour.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (72)
  1. Shape retrieval using triangle-area representation and dynamic space warping. Pattern recognition 40, 7 (2007), 1911–1920.
  2. Contour detection and hierarchical image segmentation. IEEE transactions on pattern analysis and machine intelligence 33, 5 (2010), 898–916.
  3. Integrating contour and skeleton for shape classification. In 2009 IEEE 12th international conference on computer vision workshops, ICCV workshops. IEEE, 360–367.
  4. InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules. arXiv preprint arXiv:2308.13897 (2023).
  5. Where and how: Mitigating confusion in neural radiance fields from sparse inputs. In Proceedings of the 31st ACM International Conference on Multimedia. 2180–2188.
  6. Shape matching and object recognition using shape contexts. IEEE transactions on pattern analysis and machine intelligence 24, 4 (2002), 509–522.
  7. Deepedge: A multi-scale bifurcated deep network for top-down contour detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4380–4389.
  8. Daniel Boley. 1998. Principal direction divisive partitioning. Data mining and knowledge discovery 2, 4 (1998), 325–344.
  9. DCAN: Deep contour-aware networks for object instance segmentation from histology images. Medical image analysis 36 (2017), 135–146.
  10. GC-H Chuang and C-CJ Kuo. 1996. Wavelet descriptor of planar curves: Theory and applications. IEEE Transactions on Image Processing 5, 1 (1996), 56–70.
  11. Shape description using cubic polynomial Bezier curves. Pattern Recognition Letters 19, 9 (1998), 821–828.
  12. Laurent D Cohen. 1991. On active contour models and balloons. CVGIP: Image understanding 53, 2 (1991), 211–218.
  13. Active shape models-their training and application. Computer vision and image understanding 61, 1 (1995), 38–59.
  14. Contour, color and shape analysis beyond the striate cortex. Vision research 25, 3 (1985), 441–452.
  15. Tianyu Ding. 2021. Subspace learning for data arising from a union of subspaces of high relative dimension. Ph. D. Dissertation. Johns Hopkins University.
  16. Noisy Dual Principal Component Pursuit.. In ICML. 1617–1625.
  17. Dual principal component pursuit for learning a union of hyperplanes: Theory and algorithms. In International Conference on Artificial Intelligence and Statistics. PMLR, 2944–2952.
  18. Dual principal component pursuit for robust subspace learning: Theory and algorithms for a holistic approach. In International Conference on Machine Learning. PMLR, 2739–2748.
  19. Gregory Dudek and John K Tsotsos. 1997. Shape representation and recognition from multiscale curvature. Computer vision and Image understanding 68, 2 (1997), 170–189.
  20. James H Elder. 2018. Shape from contour: Computation and representation. Annual review of vision science 4 (2018), 423–450.
  21. The pascal visual object classes (voc) challenge. International journal of computer vision 88, 2 (2010), 303–338.
  22. A review on deep learning techniques applied to semantic segmentation. arXiv preprint arXiv:1704.06857 (2017).
  23. Are we ready for autonomous driving? the kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition. IEEE, 3354–3361.
  24. Spyros Gidaris and Nikos Komodakis. 2015. Object detection via a multi-region and semantic segmentation-aware cnn model. In Proceedings of the IEEE international conference on computer vision. 1134–1142.
  25. Ross Girshick. 2015. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision. 1440–1448.
  26. An overview of contour detection approaches. International Journal of Automation and Computing 15, 6 (2018), 656–672.
  27. Steve R Gunn and Mark S Nixon. 1997. A robust snake implementation; a dual active contour. IEEE Transactions on pattern analysis and machine intelligence 19, 1 (1997), 63–68.
  28. Semantic contours from inverse detectors. In 2011 international conference on computer vision. IEEE, 991–998.
  29. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision. 2961–2969.
  30. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840–6851.
  31. Snakes: Active contour models. International journal of computer vision 1, 4 (1988), 321–331.
  32. Jan J Koenderink. 1984. What does the occluding contour tell us about solid shape? Perception 13, 3 (1984), 321–330.
  33. Gilad Lerman and Tyler Maunu. 2018a. Fast, robust and non-convex subspace recovery. Information and Inference: A Journal of the IMA 7, 2 (2018), 277–336.
  34. Gilad Lerman and Tyler Maunu. 2018b. An overview of robust subspace recovery. Proc. IEEE 106, 8 (2018), 1380–1410.
  35. A multi-angle shape descriptor with the distance ratio to vertical bounding rectangles. In 2021 International Conference on Content-Based Multimedia Indexing (CBMI). IEEE, 1–4.
  36. Polytransform: Deep polygon transformer for instance segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9131–9140.
  37. Microsoft coco: Common objects in context. In European conference on computer vision. Springer, 740–755.
  38. Fast interactive object annotation with curve-gcn. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5257–5266.
  39. Dance: A deep attentive contour model for efficient instance segmentation. In Proceedings of the IEEE/CVF winter conference on applications of computer vision. 345–354.
  40. Miles Lopes. 2013. Estimating unknown sparsity in compressed sensing. In International Conference on Machine Learning. PMLR, 217–225.
  41. A linear time algorithm for computing exact Euclidean distance transforms of binary images in arbitrary dimensions. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 2 (2003), 265–270.
  42. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65, 1 (2021), 99–106.
  43. Image segmentation using deep learning: A survey. IEEE transactions on pattern analysis and machine intelligence (2021).
  44. Farzin Mokhtarian and Alan K Mackworth. 1992. A theory of multiscale, curvature-based shape representation for planar curves. IEEE transactions on pattern analysis and machine intelligence 14, 8 (1992), 789–805.
  45. Eigencontours: Novel contour descriptors based on low-rank approximation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2667–2675.
  46. Daniel Carlos Guimarães Pedronette and Ricardo da Silva Torres. 2010. Shape retrieval using contour features and distance optimization.. In VISAPP (2). Citeseer, 197–202.
  47. Deep snake for real-time instance segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8533–8542.
  48. Juan-Carlos Perez and Enrique Vidal. 1994. Optimum polygonal approximation of digitized curves. Pattern recognition letters 15, 8 (1994), 743–750.
  49. Amodal instance segmentation with kins dataset. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3014–3023.
  50. Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018).
  51. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015).
  52. Deepcontour: A deep convolutional feature learned by positive-sharing loss for contour detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3982–3991.
  53. Contour-based learning for object detection. In Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, Vol. 1. IEEE, 503–510.
  54. Xin Shu and Xiao-Jun Wu. 2011. A novel contour descriptor for 2D shape matching and its application to image retrieval. Image and vision Computing 29, 4 (2011), 286–294.
  55. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256–2265.
  56. Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE/CVF international conference on computer vision. 9627–9636.
  57. Manolis C Tsakiris and René Vidal. 2015. Dual principal component pursuit. In Proceedings of the IEEE International Conference on Computer Vision Workshops. 10–18.
  58. A survey on shape correspondence. In Computer graphics forum, Vol. 30. Wiley Online Library, 1681–1707.
  59. Peter J Van Otterloo. 1991. A contour-oriented approach to shape analysis. Prentice Hall International (UK) Ltd.
  60. Remco C Veltkamp and Michiel Hagedoorn. 2001. State of the art in shape matching. Principles of visual information retrieval (2001), 87–119.
  61. Linear subspace design for real-time shape deformation. ACM Transactions on Graphics (TOG) 34, 4 (2015), 1–11.
  62. 2D shape deformation using nonlinear least squares optimization. The visual computer 22, 9 (2006), 653–660.
  63. Polarmask: Single shot instance segmentation with polar representation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 12193–12202.
  64. Explicit shape encoding for real-time instance segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 5168–5177.
  65. Object contour detection with a fully convolutional encoder-decoder network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 193–202.
  66. Dense reppoints: Representing visual objects with dense point sets. In European Conference on Computer Vision. Springer, 227–244.
  67. Circularity, solidity, axes of a best fit ellipse, aspect ratio, and roundness of the foramen ovale: a morphometric analysis with neurosurgical considerations. The Journal of craniofacial surgery 27, 1 (2016), 222.
  68. A comparative study on shape retrieval using Fourier descriptors with different shape signatures. In Proc. of international conference on intelligent multimedia and distance education (ICIMADE01). Citeseer, 1–9.
  69. DREAM: Diffusion Rectification and Estimation-Adaptive Models. arXiv preprint arXiv:2312.00210 (2023).
  70. Cia-net: Robust nuclei instance segmentation with contour-aware information aggregation. In International conference on information processing in medical imaging. Springer, 682–693.
  71. CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering. arXiv preprint arXiv:2311.15510 (2023).
  72. A linearly convergent method for non-smooth non-convex optimization on the grassmannian with applications to robust subspace and dictionary learning. Advances in Neural Information Processing Systems 32 (2019).

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets