PatchMatchGraph: Building a Graph of Dense Patch Correspondences for Label Transfer

详细信息    查看全文

• 作者：Stephen Gould (1) stephen.gould@anu.edu.au
  Yuhang Zhang (1) yuhang.zhang@anu.edu.au
• 刊名：Lecture Notes in Computer Science
• 出版年：2012
• 出版时间：2012
• 年：2012
• 卷：7576
• 期：1
• 页码：439-452
• 全文大小：2.6 MB
• 参考文献：1. Agarwal, S., Snavely, N., Simon, I., Seitz, S.M., Szeliski, R.: Building rome in a day. In: ICCV (2009)
  2. Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: A randomized correspondence algorithm for structural image editing. In: SIGGRAPH (2009)
  3. Barnes, C., Shechtman, E., Goldman, D.B., Finkelstein, A.: The Generalized PatchMatch Correspondence Algorithm. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 29–43. Springer, Heidelberg (2010)
  4. Bleyer, M., Rhemann, C., Rother, C.: PatchMatch stereo—stereo matching with slanted support windows. In: BMVC (2011)
  5. Criminisi, A.: Microsoft Research Rcambridge (MSRC) object recognition pixel-wise labeled image database (version 2) (2004)
  6. Gammeter, S., Bossard, L., Quack, T., Gool, L.V.: I know what you did last summer: object-level auto-annotation of holiday snaps. In: ICCV (2009)
  7. Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing, pp. 518–529 (1999)
  8. Gould, S., Fulton, R., Koller, D.: Decomposing a scene into geometric and semantically consistent regions. In: ICCV (2009)
  9. He, X., Zemel, R.S., Carreira-Perpinan, M.: Multiscale conditional random fields for image labeling. In: CVPR (2004)
  10. Heath, K., Gelfand, N., Ovsjanikov, M., Aanjaneya, M., Guibas, L.J.: Image Webs: Computing and exploiting connectivity in image collections. In: CVPR (2010)
  11. Indyk, P., Motwani, R.: Approximate nearest neighbor—towards removing the curse of dimensionality. In: 30th Symp. of Theory of Comp., pp. 604–613 (1998)
  12. Krahenbuhl, P., Koltun, V.: Efficient inference in fully connected CRFs with gaussian edge potentials. In: NIPS (2011)
  13. Ladicky, L., Russell, C., Kohli, P., Torr, P.H.: Associative hierarchical CRFs for object class image segmentation. In: ICCV (2009)
  14. Li, Y., Crandall, D., Huttenlocher, D.: Landmark classification in large-scale image collections. In: ICCV (2009)
  15. Liu, C., Yuen, J., Torralba, A.: Nonparametric scene parsing: Label transfer via dense scene alignment. In: CVPR (2009)
  16. Liu, C., Yuen, J., Torralba, A.: Nonparametric scene parsing via label transfer. PAMI 33(12), 2368–2382 (2011)
  17. Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. IJCV 42(3), 145–175 (2001)
  18. Shotton, J., Winn, J., Rother, C., Criminisi, A.: TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 1–15. Springer, Heidelberg (2006)
  19. Tighe, J., Lazebnik, S.: SuperParsing: Scalable Nonparametric Image Parsing with Superpixels. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 352–365. Springer, Heidelberg (2010)
  20. Zhang, H., Quan, L.: Partial similarity based nonparametric scene parsing in certain environment. In: CVPR (2011)
• 作者单位：1. Research School of Computer Science, ANU, Australia
• ISSN：1611-3349

文摘

We address the problem of semantic segmentation, or multi-class pixel labeling, by constructing a graph of dense overlapping patch correspondences across large image sets. We then transfer annotations from labeled images to unlabeled images using the established patch correspondences. Unlike previous approaches to non-parametric label transfer our approach does not require an initial image retrieval step. Moreover, we operate on a graph for computing mappings between images, which avoids the need for exhaustive pairwise comparisons. Consequently, we can leverage offline computation to enhance performance at test time. We conduct extensive experiments to analyze different variants of our graph construction algorithm and evaluate multi-class pixel labeling performance on several challenging datasets.