Abstract
Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a deep shape representation that enables encoding and reconstruction of high-quality 3D shapes without prohibitive memory requirements. DeepLS replaces the dense volumetric signed distance function (SDF) representation used in traditional surface reconstruction systems with a set of locally learned continuous SDFs defined by a neural network, inspired by recent work such as DeepSDF. Unlike DeepSDF, which represents an object-level SDF with a neural network and a single latent code, we store a grid of independent latent codes, each responsible for storing information about surfaces in a small local neighborhood. This decomposition of scenes into local shapes simplifies the prior distribution that the network must learn, and also enables efficient inference. We demonstrate the effectiveness and generalization power of DeepLS by showing object shape encoding and reconstructions of full scenes, where DeepLS delivers high compression, accuracy, and local shape completion.
R. Chabra and J. E. Lenssen—Work performed during an internship at Facebook Reality Labs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
3D Warehouse. https://3dwarehouse.sketchup.com/
Stanford 3D Scanning Repository. http://graphics.stanford.edu/data/3Dscanrep/
Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds (2017). arXiv preprint arXiv:1707.02392
Aroudj, S., Seemann, P., Langguth, F., Guthe, S., Goesele, M.: Visibility-consistent thin surface reconstruction using multi-scale kernels. ACM Trans. Graph. (TOG) 36(6), 187 (2017)
Ben-Hamu, H., Maron, H., Kezurer, I., Avineri, G., Lipman, Y.: Multi-chart generative surface modeling. In: SIGGRAPH Asia 2018 Technical Papers, p. 215. ACM (2018)
Blinn, J.F.: A generalization of algebraic surface drawing. ACM Trans. Graph. (TOG) 1(3), 235–256 (1982)
Calakli, F., Taubin, G.: Ssd: smooth signed distance surface reconstruction. In: Computer Graphics Forum. vol. 30, pp. 1993–2002. Wiley Online Library (2011)
Carr, J.C., et al.: Reconstruction and representation of 3D objects with radial basis functions. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, pp. 67–76. ACM (2001)
Chabra, R., Straub, J., Sweeney, C., Newcombe, R., Fuchs, H.: Stereodrnet: dilated residual stereonet. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11786–11795 (2019)
Chen, Z., Zhang, H.: Learning implicit fields for generative shape modeling. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Choy, C.B., Xu, D., Gwak, J.Y., Chen, K., Savarese, S.: 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 628–644. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_38
Curless, B., Levoy, M.: A volumetric method for building complex models from range images (1996)
Dai, A., Nießner, M.: Scan2mesh: from unstructured range scans to 3D meshes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5574–5583 (2019)
Dai, A., Ruizhongtai Qi, C., Nießner, M.: Shape completion using 3D-encoder-predictor CNNs and shape synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5868–5877 (2017)
Deng, B., Genova, K., Yazdani, S., Bouaziz, S., Hinton, G., Tagliasacchi, A.: Cvxnets: learnable convex decomposition (2019)
Fuhrmann, S., Goesele, M.: Floating scale surface reconstruction. ACM Trans. Graph. (ToG) 33(4), 46 (2014)
Gal, R., Shamir, A., Hassner, T., Pauly, M., Cohen-Or, D.: Surface reconstruction using local shape priors. In: Symposium on Geometry Processing, No. CONF, pp. 253–262 (2007)
Genova, K., Cole, F., Sud, A., Sarna, A., Funkhouser, T.: Deep structured implicit functions (2019). arXiv preprint arXiv:1912.06126
Genova, K., Cole, F., Vlasic, D., Sarna, A., Freeman, W.T., Funkhouser, T.: Learning shape templates with structured implicit functions (2019). arXiv preprint arXiv:1904.06447
Gkioxari, G., Malik, J., Johnson, J.: Mesh r-cnn (2019). arXiv preprint arXiv:1906.02739
Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: Atlasnet: apapier-m\(\backslash \) ach\(\backslash \) approach to learning 3D surfacegeneration (2018). arXiv preprint arXiv:1802.05384
Handa, A., Whelan, T., McDonald, J., Davison, A.: A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM. In: IEEE International Conference on Robotics and Automation, ICRA. Hong Kong, China (2014)
Häne, C., Tulsiani, S., Malik, J.: Hierarchical surface prediction for 3D object reconstruction. In: 2017 International Conference on 3D Vision (3DV), pp. 412–420. IEEE (2017)
Hoppe, H., DeRose, T., Duchamp, T., McDonald, J., Stuetzle, W.: Surface reconstruction from unorganized points. In: Proceedings of the 19th Annual Conference on Computer Graphics and Interactive Techniques, pp. 71–78 (1992)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)
Jancosek, M., Pajdla, T.: Multi-view reconstruction preserving weakly-supported surfaces. In: CVPR 2011, pp. 3121–3128. IEEE (2011)
Jiang, C., Sud, A., Makadia, A., Huang, J., Nießner, M., Funkhouser, T.: Local implicit grid representations for 3D scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)
Kazhdan, M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Proceedings of the Fourth Eurographics Symposium on Geometry Processing, vol. 7 (2006)
Kazhdan, M., Hoppe, H.: Screened poisson surface reconstruction. ACM Trans. Graph. (ToG) 32(3), 1–13 (2013)
Keller, M., Lefloch, D., Lambers, M., Izadi, S., Weyrich, T., Kolb, A.: Real-time 3D reconstruction in dynamic scenes using point-based fusion. In: 2013 International Conference on 3D Vision-3DV 2013, pp. 1–8. IEEE (2013)
Klein, G., Murray, D.: Parallel tracking and mapping for small ar workspaces. In: Proceedings of the 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality, pp. 1–10. IEEE Computer Society (2007)
Labatut, P., Pons, J.P., Keriven, R.: Robust and efficient surface reconstruction from range data. In: Computer Graphics Forum, vol. 28, pp. 2275–2290. Wiley Online Library (2009)
Liao, Y., Donne, S., Geiger, A.: Deep marching cubes: learning explicit surface representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2916–2925 (2018)
Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4460–4470 (2019)
Michalkiewicz, M., Pontes, J.K., Jack, D., Baktashmotlagh, M., Eriksson, A.: Deep level sets: implicit surface representations for 3D shape inference (2019). arXiv preprint arXiv:1901.06802
Newcombe, R.A., Davison, A.J.: Live dense reconstruction with a single moving camera. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1498–1505. IEEE (2010)
Newcombe, R.A., et al.: Kinectfusion: real-time dense surface mapping and tracking. In: 2011 10th IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 127–136. IEEE (2011)
Ohtake, Y., Belyaev, A., Alexa, M., Turk, G., Seidel, H.P.: Multi-level partition of unity implicits. In: Acm Siggraph 2005 Courses, pp. 173-es (2005)
Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: Deepsdf: learning continuous signed distance functions for shape representation (2019). arXiv preprint arXiv:1901.05103
Pfister, H., Zwicker, M., Van Baar, J., Gross, M.: Surfels: surface elements as rendering primitives. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 335–342. ACM Press/Addison-Wesley Publishing Co. (2000)
Ricao Canelhas, D., Schaffernicht, E., Stoyanov, T., Lilienthal, A., Davison, A.: Compressed voxel-based mapping using unsupervised learning. Robotics 6(3), 15 (2017)
Riegler, G., Osman Ulusoy, A., Geiger, A.: Octnet: learning deep 3D representations at high resolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3577–3586 (2017)
Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: Pifu: pixel-aligned implicit function for high-resolution clothed human digitization (2019). arXiv preprint arXiv:1905.05172
Sinha, A., Bai, J., Ramani, K.: Deep learning 3D shape surfaces using geometry images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 223–240. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_14
Straub, J., et al.: The Replica dataset: a digital replica of indoor spaces (2019). arXiv preprint arXiv:1906.05797
Stühmer, J., Gumhold, S., Cremers, D.: Real-time dense geometry from a handheld camera. In: Goesele, M., Roth, S., Kuijper, A., Schiele, B., Schindler, K. (eds.) DAGM 2010. LNCS, vol. 6376, pp. 11–20. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15986-2_2
Stutz, D., Geiger, A.: Learning 3D shape completion from laser scan data with weak supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1955–1964 (2018)
Tatarchenko, M., Dosovitskiy, A., Brox, T.: Octree generating networks: efficient convolutional architectures for high-resolution 3D outputs. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2088–2096 (2017)
Ummenhofer, B., Brox, T.: Global, dense multiscale reconstruction for a billion points. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1341–1349 (2015)
Whelan, T., et al.: Reconstructing scenes with mirror and glass surfaces. ACM Trans. Graph. (TOG) 37(4), 102 (2018)
Whelan, T., Leutenegger, S., Salas-Moreno, R., Glocker, B., Davison, A.: Elasticfusion: Dense slam without a pose graph. Robotics: Science and Systems (2015)
Williams, F., Schneider, T., Silva, C., Zorin, D., Bruna, J., Panozzo, D.: Deep geometric prior for surface reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10130–10139 (2019)
Wu, Z., et al.: 3d shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912–1920 (2015)
Xu, Q., Wang, W., Ceylan, D., Mech, R., Neumann, U.: Disn: deep implicit surface network for high-quality single-view 3D reconstruction (2019). arXiv preprint arXiv:1905.10711
Yang, Y., Feng, C., Shen, Y., Tian, D.: Foldingnet: interpretable unsupervised learning on 3D point clouds (2017). arXiv preprint arXiv:1712.07262
Yuan, W., Khot, T., Held, D., Mertz, C., Hebert, M.: Pcn: point completion network. In: 2018 International Conference on 3D Vision (3DV), pp. 728–737. IEEE (2018)
Zhou, Q.Y., Koltun, V.: Dense scene reconstruction with points of interest. ACM Trans. Graph. (ToG) 32(4), 1–8 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Chabra, R. et al. (2020). Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12374. Springer, Cham. https://doi.org/10.1007/978-3-030-58526-6_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-58526-6_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58525-9
Online ISBN: 978-3-030-58526-6
eBook Packages: Computer ScienceComputer Science (R0)