Abstract
We present a novel approach to infer volumetric reconstructions from a single viewport, based only on an RGB image and a reconstructed normal image. To overcome the problem of reconstructing regions in 3D that are occluded in the 2D image, we propose to learn this information from synthetically generated high-resolution data. To do this, we introduce a deep network architecture that is specifically designed for volumetric TSDF data by featuring a specific tree net architecture. Our framework can handle a 3D resolution of \(512^3\) by introducing a dedicated compression technique based on a modified autoencoder. Furthermore, we introduce a novel loss shaping technique for 3D data that guides the learning process towards regions where free and occupied space are close to each other. As we show in experiments on synthetic and realistic benchmark data, this leads to very good reconstruction results, both visually and in terms of quantitative measures.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: International Conference on 3D Vision (3DV) (2017)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)
Dai, A., Ritchie, D., Bokeloh, M., Reed, S., Sturm, J., Nießner, M.: ScanComplete: large-scale scene completion and semantic segmentation for 3D scans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4578–4587 (2018)
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)
Denninger, M., et al.: Blenderproc. arXiv:1911.01911 (2019)
Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems, pp. 2366–2374 (2014)
Firman, M., Mac Aodha, O., Julier, S., Brostow, G.J.: Structured prediction of unobserved voxels from a single depth image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5431–5440 (2016)
Hane, C., Zach, C., Cohen, A., Angst, R., Pollefeys, M.: Joint 3D scene reconstruction and class segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 97–104 (2013)
Hausdorff, F.: Grundzüge der mengenlehre. de Gruyter & Co., Leipzig, 1927, 1935 (1914)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Izadinia, H., Shan, Q., Seitz, S.M.: Im2cad. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5134–5143 (2017)
Kim, H., Moon, J., Lee, B.: RGB-to-TSDF: Direct TSDF prediction from a single RGB image for dense 3D reconstruction. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6714–6720. IEEE (2019)
Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5162–5170 (2015)
Liu, F., Shen, C., Lin, G., Reid, I.: Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2024–2039 (2015)
Mal, F., Karaman, S.: Sparse-to-dense: depth prediction from sparse depth samples and a single image. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–8. IEEE (2018)
Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. arXiv:1901.05103 (2019)
Richter, S.R., Roth, S.: Matryoshka networks: predicting 3D geometry via nested shape layers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1936–1944 (2018)
Rock, J., Gupta, T., Thorsen, J., Gwak, J., Shin, D., Hoiem, D.: Completing 3D object shape from one depth image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2484–2493 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28. https://lmb.informatik.uni-freiburg.de/Publications/2015/RFB15a/. (available on arXiv:1505.04597 [cs.CV])
Silberman, N., Shapira, L., Gal, R., Kohli, P.: A contour completion model for augmenting surface reconstructions. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 488–503. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_32
Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. arXiv:1611.08974 (2016)
Straub, J., et al.: The replica dataset: a digital replica of indoor spaces. arXiv:1906.05797 (2019)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
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)
Thanh Nguyen, D., Hua, B.S., Tran, K., Pham, Q.H., Yeung, S.K.: A field model for repairing 3D shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5676–5684 (2016)
Varley, J., DeChant, C., Richardson, A., Ruales, J., Allen, P.: Shape completion enabled robotic grasping. In: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2442–2447. IEEE (2017)
Wu, J., Zhang, C., Zhang, X., Zhang, Z., Freeman, W.T., Tenenbaum, J.B.: Learning shape priors for single-view 3D completion and reconstruction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 673–691. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_40
Wu, Y., Man, J., Xie, Z.: A double layer method for constructing signed distance fields from triangle meshes. Graph. Models 76(4), 214–223 (2014)
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)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122 (2015)
Zhang, Y., Funkhouser, T.: Deep depth completion of a single RGB-D image. arXiv:1803.09326 (2018)
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.
Supplementary material 2 (mp4 94918 KB)
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Denninger, M., Triebel, R. (2020). 3D Scene Reconstruction from a Single Viewport. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12367. Springer, Cham. https://doi.org/10.1007/978-3-030-58542-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-58542-6_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58541-9
Online ISBN: 978-3-030-58542-6
eBook Packages: Computer ScienceComputer Science (R0)