Abstract
We present an end-to-end 3D reconstruction method for a scene by directly regressing a truncated signed distance function (TSDF) from a set of posed RGB images. Traditional approaches to 3D reconstruction rely on an intermediate representation of depth maps prior to estimating a full 3D model of a scene. We hypothesize that a direct regression to 3D is more effective. A 2D CNN extracts features from each image independently which are then back-projected and accumulated into a voxel volume using the camera intrinsics and extrinsics. After accumulation, a 3D CNN refines the accumulated features and predicts the TSDF values. Additionally, semantic segmentation of the 3D model is obtained without significant computation. This approach is evaluated on the Scannet dataset where we significantly outperform state-of-the-art baselines (deep multiview stereo followed by traditional TSDF fusion) both quantitatively and qualitatively. We compare our 3D semantic segmentation to prior methods that use a depth sensor since no previous work attempts the problem with only RGB input.
T. van As, J. Bartolozzi and V. Badrinarayanan—Work done at Magic Leap.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation (2015)
Chabra, R., et al.: Deep local shapes: learning local SDF priors for detailed 3D reconstruction. ar**v preprint ar**v:2003.10983 (2020)
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)
Chang, A.X., et al.: Shapenet: an information-rich 3D model repository. ar**v preprint ar**v:1512.03012 (2015)
Chang, J.R., Chen, Y.S.: Pyramid stereo matching network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5410–5418 (2018)
Chen, R., Han, S., Xu, J., Su, H.: Point-based multi-view stereo network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1538–1547 (2019)
Cheng, B., et al.: Panoptic-deeplab. ar**v preprint ar**v:1910.04751 (2019)
Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: minkowski convolutional neural networks (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. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, pp. 303–312 (1996)
Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of Computer Vision and Pattern Recognition (CVPR). IEEE (2017)
Dai, A., Diller, C., Nießner, M.: SG-NN: sparse generative neural networks for self-supervised scene completion of RGB-D scans. ar**v preprint ar**v:1912.00036 (2019)
Dai, A., Nießner, M.: 3DMV: joint 3D-multi-view prediction for 3D semantic scene segmentation (2018)
Dai, A., Qi, C.R., Nießner, M.: Shape completion using 3D-encoder-predictor CNNs and shape synthesis (2016)
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)
Falcon, W.: Pytorch lightning. GitHub. https://github.com/PyTorchLightning/pytorch-lightning Cited by 3 (2019)
Fan, H., Su, H., Guibas, L.J.: A point set generation network for 3D object reconstruction from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 605–613 (2017)
Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2002–2011 (2018)
Galliani, S., Lasinger, K., Schindler, K.: Massively parallel multiview stereopsis by surface normal diffusion. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 873–881 (2015)
Gkioxari, G., Malik, J., Johnson, J.: Mesh R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9785–9795 (2019)
Graham, B., Engelcke, M., van der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9224–9232 (2018)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
Hirschmuller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 328–341 (2007)
Hou, J., Dai, A., Nießner, M.: 3D-SIC: 3D semantic instance completion for RGB-D scans. ar**v preprint ar**v:1904.12012 (2019)
Hou, J., Dai, A., Nießner, M.: 3D-SIS: 3D semantic instance segmentation of RGB-D scans (2018)
Hou, Y., Kannala, J., Solin, A.: Multi-view stereo by temporal nonparametric fusion. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2651–2660 (2019)
Huang, P.H., Matzen, K., Kopf, J., Ahuja, N., Huang, J.B.: Deepmvs: learning multi-view stereopsis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2821–2830 (2018)
Im, S., Jeon, H.G., Lin, S., Kweon, I.S.: Dpsnet: end-to-end deep plane sweep stereo. In: 7th International Conference on Learning Representations, ICLR 2019. International Conference on Learning Representations, ICLR (2019)
Iskakov, K., Burkov, E., Lempitsky, V., Malkov, Y.: Learnable triangulation of human pose. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7718–7727 (2019)
Kirillov, A., Girshick, R., He, K., Dollár, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6399–6408 (2019)
Lasinger, K., Ranftl, R., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. ar**v preprint ar**v:1907.01341 (2019)
Lee, J.H., Han, M.K., Ko, D.W., Suh, I.H.: From big to small: multi-scale local planar guidance for monocular depth estimation. ar**v preprint ar**v:1907.10326 (2019)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. ACM Siggraph Comput. Graph. 21(4), 163–169 (1987)
McCormac, J., Clark, R., Bloesch, M., Davison, A., Leutenegger, S.: Fusion++: volumetric object-level slam. In: 2018 International Conference on 3D Vision (3DV), pp. 32–41. IEEE (2018)
McCormac, J., Handa, A., Davison, A., Leutenegger, S.: Semanticfusion: dense 3D semantic map** with convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 4628–4635. IEEE (2017)
Narita, G., Seno, T., Ishikawa, T., Kaji, Y.: Panopticfusion: online volumetric semantic map** at the level of stuff and things. ar**v preprint ar**v:1903.01177 (2019)
Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: Deepsdf: learning continuous signed distance functions for shape representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 165–174 (2019)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space (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)
Rosinol, A., Abate, M., Chang, Y., Carlone, L.: Kimera: an open-source library for real-time metric-semantic localization and map**. In: IEEE International Conference on Robotics and Automation (ICRA) (2020)
Schönberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Schönberger, J.L., Zheng, E., Pollefeys, M., Frahm, J.M.: Pixelwise view selection for unstructured multi-view stereo. In: European Conference on Computer Vision (ECCV) (2016)
Schöps, T., Sattler, T., Pollefeys, M.: Surfelmeshing: online surfel-based mesh reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. (2019)
Sinha, A., Unmesh, A., Huang, Q., Ramani, K.: Surfnet: generating 3D shape surfaces using deep residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6040–6049 (2017)
Sitzmann, V., Thies, J., Heide, F., Nießner, M., Wetzstein, G., Zollhofer, M.: Deepvoxels: learning persistent 3D feature embeddings. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2437–2446 (2019)
Sitzmann, V., Zollhöfer, M., Wetzstein, G.: Scene representation networks: continuous 3D-structure-aware neural scene representations. In: Advances in Neural Information Processing Systems (2019)
Su, H., et al.: Splatnet: sparse lattice networks for point cloud processing (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)
Tateno, K., Tombari, F., Laina, I., Navab, N.: CNN-slam: real-time dense monocular slam with learned depth prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6243–6252 (2017)
Wang, K., Shen, S.: Mvdepthnet: real-time multiview depth estimation neural network. In: 2018 International Conference on 3D Vision (3DV), pp. 248–257. IEEE (2018)
Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W., Jiang, Y.G.: Pixel2Mesh: generating 3D mesh models from single RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 52–67 (2018)
Wang, W., Yu, R., Huang, Q., Neumann, U.: SGPN: similarity group proposal network for 3D point cloud instance segmentation. In: In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2569–2578 (2018)
Weder, S., Schönberger, J., Pollefeys, M., Oswald, M.R.: Routedfusion: learning real-time depth map fusion. ar**v preprint ar**v:2001.04388 (2020)
Whelan, T., Leutenegger, S., Salas-Moreno, R., Glocker, B., Davison, A.: Elasticfusion: Dense slam without a pose graph. Robotics: Science and Systems (2015)
**e, H., Yao, H., Sun, X., Zhou, S., Zhang, S.: Pix2Vox: context-aware 3D reconstruction from single and multi-view images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2690–2698 (2019)
Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: Mvsnet: depth inference for unstructured multi-view stereo. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 767–783 (2018)
Yao, Y., Luo, Z., Li, S., Shen, T., Fang, T., Quan, L.: Recurrent MVSNet for high-resolution multi-view stereo depth inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5525–5534 (2019)
Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: FreiHAND: a dataset for markerless capture of hand pose and shape from single RGB images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 813–822 (2019)
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 1 (m4v 84704 KB)
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Murez, Z., van As, T., Bartolozzi, J., Sinha, A., Badrinarayanan, V., Rabinovich, A. (2020). Atlas: End-to-End 3D Scene Reconstruction from Posed Images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12352. Springer, Cham. https://doi.org/10.1007/978-3-030-58571-6_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-58571-6_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58570-9
Online ISBN: 978-3-030-58571-6
eBook Packages: Computer ScienceComputer Science (R0)