Abstract
We propose a novel hierarchy construction algorithm for 3D scenes with repeated elements, such as classrooms with multiple desk–chair pairs. Most existing algorithms focus on scenes such as bedrooms or living rooms, which rarely contain repeated patterns. Consequently, such methods may not recognize repeated patterns, which are vital for understanding the structure and context of scenes such as classrooms. Therefore, we propose a new global optimization algorithm for recognizing repeated patterns and building hierarchical structures based on repeated patterns. First, we find a repeated template by calculating the coverage ratios and frequencies of many substructures in a scene. Once the repeated template has been determined, a minimum cost maximum flow problem can be solved to find all instances (repetitions) of it in the scene and then group objects accordingly. Second, we group objects in the region outside the repeated elements according to their adjacency. Finally, based on these two sets of results, we build the hierarchy of the entire scene. We test this hierarchy construction algorithm on the Princeton and SceneNN databases and show that our algorithm can correctly find repeated patterns and construct a hierarchy that is more similar to the ground truth than the results of previous methods.
Similar content being viewed by others
References
Ahuja, N., Todorovic, S.: Extracting texels in 2.1D natural textures. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1–8 (2007)
Alhashim, I., Li, H., Xu, K., Cao, J., Ma, R., Zhang, H.: Topology-varying 3D shape creation via structural blending. ACM Trans. Gr. (TOG) 33(4), 158 (2014)
Bokeloh, M., Wand, M., Seidel, H.P.: A connection between partial symmetry and inverse procedural modeling. ACM Trans. Gr. (TOG) 29(4), 104 (2010)
Cheng, M.M., Zhang, F.L., Mitra, N.J., Huang, X., Hu, S.M.: RepFinder: finding approximately repeated scene elements for image editing. ACM Trans. Gr. 29(4), 1 (2010)
Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms, 3rd edn. The MIT Press, Cambridge (2009)
Fisher, M., Savva, M., Hanrahan, P.: Characterizing structural relationships in scenes using graph kernels. ACM Trans. Gr. (TOG) 30, 34 (2011)
Gal, R., Cohen-Or, D.: Salient geometric features for partial shape matching and similarity. ACM Trans. Gr. (TOG) 25(1), 130–150 (2006)
Golovinskiy, A., Funkhouser, T.: Consistent segmentation of 3D models. Comput. Gr. 33(3), 262–269 (2009)
Hu, R., Zhu, C., van Kaick, O., Liu, L., Shamir, A., Zhang, H.: Interaction context (ICON): towards a geometric functionality descriptor. ACM Trans. Gr. 34, 83:1–83:12 (2015)
Huang, H., Zhang, L., Zhang, H.C.: RepSnapping: efficient image cutout for repeated scene elements. Comput. Gr. Forum 30(7), 2059–2066 (2011)
Hueting, M., Monszpart, A., Mellado, N.: MCGraph: multi-criterion representation for scene understanding. In: SIGGRAPH Asia 2014 Indoor Scene Understanding Where Graphics Meets Vision, p. 3. ACM (2014)
Kalogerakis, E., Chaudhuri, S., Koller, D., Koltun, V.: A probabilistic model for component-based shape synthesis. ACM Trans. Gr. (TOG) 31(4), 55 (2012)
Li, J., Xu, K., Chaudhuri, S., Yumer, E., Zhang, H., Guibas, L.: GRASS: generative recursive autoencoders for shape structures. ACM Trans. Gr. 36(4), 1–12 (2017). arXiv:1705.02090
Liu, Y., Collins, R., Tsin, Y.: A computational model for periodic pattern perception based on frieze and wallpaper groups. IEEE Trans. Pattern Anal. Mach. Intell. 26(3), 354–371 (2004)
Liu, S., Martin, R.R., Langbein, F.C., Rosin, P.L.: Segmenting periodic reliefs on triangle meshes. In: Martin, R., Sabin, M., Winkler, J. (eds.) Mathematics of Surfaces XII, vol. 4647, pp. 290–306. Springer, Berlin (2007)
Liu, T., Chaudhuri, S., Kim, V.G., Huang, Q., Mitra, N.J., Funkhouser, T.: Creating consistent scene graphs using a probabilistic grammar. ACM Trans. Gr. 33(6), 211:1–211:12 (2014)
MacDonald, D., Lang, J., McAllister, M.: Evaluation of colour image segmentation hierarchies. In: The 3rd Canadian Conference on Computer and Robot Vision, 2006, p. 27 (2006)
Mitra, N., Wand, M., Zhang, H.R., Cohen-Or, D., Kim, V., Huang, Q.X.: Structure-aware shape processing. In: SIGGRAPH Asia 2013 Courses, SA ’13, pp. 1:1–1:20. ACM, New York (2013)
Moulin, M., Dutré, P.: On the use of local ray termination for efficiently constructing qualitative BSPs, BIHs and (S)BVHs. Vis. Comput. (2018). https://doi.org/10.1007/s00371-018-1575-x
Nguyen, D.T., Hua, B.S., Yu, L.F., Yeung, S.K.: A Robust 3D–2D Interactive Tool for Scene Segmentation and Annotation (2016). arXiv:1610.05883 [cs]. arXiv:1610.05883
Paraboschi, L., Biasotti, S., Falcidieno, B.: 3D scene comparison using topological graphs. In: Eurographics Italian Chapter Conference, pp. 87–93 (2007)
Sappa, A.D., Garcia, M.A.: Generating compact representations of static scenes by means of 3D object hierarchies. Vis. Comput. 23(2), 143–154 (2007)
Sidi, O., van Kaick, O., Kleiman, Y., Zhang, H., Cohen-Or, D.: Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering. ACM Trans. Gr. (TOG) 30, 126 (2011)
Wang, Y., Xu, K., Li, J., Zhang, H., Shamir, A., Liu, L., Cheng, Z., Xiong, Y.: Symmetry hierarchy of man-made objects. In: Computer Graphics Forum, vol. 30, pp. 287–296. Wiley Online Library (2011)
Xu, K., Ma, R., Zhang, H., Zhu, C., Shamir, A., Cohen-Or, D., Huang, H.: Organizing heterogeneous scene collections through contextual focal points. ACM Trans. Gr. (TOG) 33(4), 35 (2014)
Zhang, F.-L., Cheng, M.-M., Jia, J., Shi-Min, H.: ImageAdmixture: putting together dissimilar objects from groups. IEEE Trans. Vis. Comput. Gr. 18(11), 1849–1857 (2012)
Zhao, X., Hu, R., Guerrero, P., Mitra, N., Komura, T.: Relationship templates for creating scene variations. ACM Trans. Gr. 35(6), 207:1–207:13 (2016)
Zhao, X., Wang, H., Komura, T.: Indexing 3D scenes using the interaction bisector surface. ACM Trans. Gr. (TOG) 33(3), 22:1–22:14 (2014)
Funding
This study was funded by the National Natural Science Foundation of China (61602366) and the China Postdoctoral Science Foundation (2015M582664).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Proof that the flow network contains no negative-cost cycles
Proof that the flow network contains no negative-cost cycles
The Floyd–Warshall method works only when the network contains no negative-cost cycles. Therefore, we need to prove here that the directed cost graph from which we find the minimum path satisfies this condition. According to the Ford–Fulkerson method, we iteratively repeat two steps: (1) searching for an augmenting path in the cost network and (2) updating the cost network (corresponding to the matrix w in the algorithm) after adding the new augmenting path. The cost network may have two types of edges: positive edges, which have the same directions and cost values C(i, j) as those of the corresponding original edges in the flow network, and negative edges, which have the opposite directions and negative-cost values \(-C(i, j)\). Consider a cycle in a cost network, such as that shown in Fig. 11. Note that the edges connected to the source or sink in a cycle are always paired. Because we set the costs of all edges connected to the source or sink to 1, the costs of such an edge pair, such as (e(s, u1), e(u2, s)) or (e(v1, t), e(t, v2)), always cancel to zero. Thus, the total cost of the cycle is \(C_i - C_j\), where \(C_i\) is the cost of edge e(u1, v1) and \(-C_j\) is the cost of edge e(v2, u2). There is a negative-cost edge from v2 to u2, meaning that the flow of edge e(u2, v2) has been used as part of the flow solution. On the other hand, the positive-cost edge e(u1, v1) indicates that the flow of this edge has not been used. The edge e(u2, v2) is chosen earlier than e(u1, v1) indicates that e(u2, v2) has a smaller weight, so we can infer that \(C_j \le C_i\). Therefore, the cost of the cycle cannot be negative.
Rights and permissions
About this article
Cite this article
Zhao, X., Su, Z., Komura, T. et al. Building hierarchical structures for 3D scenes with repeated elements. Vis Comput 36, 361–374 (2020). https://doi.org/10.1007/s00371-018-01625-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-018-01625-y