Abstract
Implicit neural representations have shown potential advantages in 3D reconstruction. But implicit neural 3D reconstruction methods require high-performance graphical computing power, which limits their application on low power consumption platforms. Remote 3D reconstruction framework can be employed to address this issue, but the sampling method needs to be further improved.
We present a novel sampling method, QuadSampling, for remote implicit neural 3D reconstruction. By hierarchically sampling pixels within blocks with larger loss value, QuadSampling can result in larger average loss and help the neural learning process by better representing the shape of regions with different loss value. Thus, under the same amount of transmission, our QuadSampling can obtain more accurate and complete implicit neural representation of the scene. Extensive evaluations show that comparing with prior methods (i.e. random sampling and active sampling), our QuadSampling framework can improve the accuracy by up to 4%, and the completion ratio by about 1–2%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Campos, C., Elvira, R., Rodríguez, J.J.G., Montiel, J.M.M., Tardós, J.D.: ORB-SLAM3: an accurate open-source library for visual, visual-inertial, and multimap SLAM. IEEE Trans. Robot. 37(6), 1874–1890 (2021)
Chen, Z., Zhang, H.: Learning implicit fields for generative shape modeling. In: CVPR, pp. 5939–5948 (2019)
Chibane, J., Mir, A., Pons-Moll, G.: Neural unsigned distance fields for implicit function learning. In: NeurIPS (2020)
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: Fujii, J. (ed.) Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1996, New Orleans, LA, USA, 4–9 August 1996, pp. 303–312. ACM (1996)
Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T.A., Nießner, M.: ScanNet: Richly-annotated 3D reconstructions of indoor scenes. In: CVPR, pp. 2432–2443 (2017)
Deng, K., Liu, A., Zhu, J., Ramanan, D.: Depth-supervised NeRF: fewer views and faster training for free. In: CVPR, pp. 12872–12881 (2022)
Dong, S., et al.: Multi-robot collaborative dense scene reconstruction. ACM Trans. Graph. 38(4), 84:1–84:16 (2019)
Fan, H., Su, H., Guibas, L.J.: A point set generation network for 3D object reconstruction from a single image. In: CVPR, pp. 2463–2471 (2017)
Gkioxari, G., Johnson, J., Malik, J.: Mesh R-CNN. In: ICCV, pp. 9784–9794 (2019)
Golodetz, S., Cavallari, T., Lord, N.A., Prisacariu, V.A., Murray, D.W., Torr, P.H.S.: Collaborative large-scale dense 3D reconstruction with online inter-agent pose optimisation. IEEE Trans. Vis. Comput. Graph. 24(11), 2895–2905 (2018)
Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: A Papier-Mâché approach to learning 3D surface generation. In: CVPR, pp. 216–224 (2018)
Hornung, A., Wurm, K.M., Bennewitz, M., Stachniss, C., Burgard, W.: OctoMap: an efficient probabilistic 3D mapping framework based on octrees. Auton. Robots 34(3), 189–206 (2013)
Kähler, O., Prisacariu, V.A., Ren, C.Y., Sun, X., Torr, P.H.S., Murray, D.W.: Very high frame rate volumetric integration of depth images on mobile devices. IEEE Trans. Vis. Comput. Graph. 21(11), 1241–1250 (2015)
Kähler, O., Prisacariu, V.A., Valentin, J.P.C., Murray, D.W.: Hierarchical voxel block hashing for efficient integration of depth images. IEEE Robot. Autom. Lett. 1(1), 192–197 (2016)
Kanazawa, A., Tulsiani, S., Efros, A.A., Malik, J.: Learning category-specific mesh reconstruction from image collections. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 386–402. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01267-0_23
Lin, C., Kong, C., Lucey, S.: Learning efficient point cloud generation for dense 3D object reconstruction. In: AAAI, pp. 7114–7121 (2018)
Mescheder, L.M., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: CVPR, pp. 4460–4470 (2019)
Michalkiewicz, M., Pontes, J.K., Jack, D., Baktashmotlagh, M., Eriksson, A.P.: Implicit surface representations as layers in neural networks. In: ICCV, pp. 4742–4751 (2019)
Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405–421. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_24
Newcombe, R.A., et al.: KinectFusion: real-time dense surface mapping and tracking. In: 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011, Basel, Switzerland, 26–29 October 2011, pp. 127–136 (2011)
Nießner, M., Zollhöfer, M., Izadi, S., Stamminger, M.: Real-time 3D reconstruction at scale using voxel hashing. ACM Trans. Graph. 32(6), 169:1–169:11 (2013)
Park, J.J., Florence, P.R., Straub, J., Newcombe, R.A., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: CVPR, pp. 165–174 (2019)
Prokudin, S., Lassner, C., Romero, J.: Efficient learning on point clouds with basis point sets. In: ICCV, pp. 4331–4340 (2019)
Sitzmann, V., Martel, J.N.P., Bergman, A.W., Lindell, D.B., Wetzstein, G.: Implicit neural representations with periodic activation functions. In: NeurIPS (2020)
Straub, J., et al.: The replica dataset: a digital replica of indoor spaces. CoRR abs/1906.05797 (2019). http://arxiv.org/abs/1906.05797
Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D SLAM systems. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2012, Vilamoura, Algarve, Portugal, 7–12 October 2012, pp. 573–580. IEEE (2012)
Sucar, E., Liu, S., Ortiz, J., Davison, A.J.: iMAP: implicit mapping and positioning in real-time. In: ICCV, pp. 6209–6218 (2021)
Tang, D., et al.: Deep implicit volume compression. In: CVPR, pp. 1290–1300 (2020)
Wei, Y., Liu, S., Rao, Y., Zhao, W., Lu, J., Zhou, J.: NerfingMVS: guided optimization of neural radiance fields for indoor multi-view stereo. In: ICCV, pp. 5590–5599 (2021)
Wen, C., Zhang, Y., Li, Z., Fu, Y.: Pixel2mesh++: multi-view 3D mesh generation via deformation. In: ICCV, pp. 1042–1051 (2019)
Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: NeurIPS, pp. 82–90 (2016)
Wu, Z., et al.: 3D shapenets: a deep representation for volumetric shapes. In: CVPR, pp. 1912–1920 (2015)
Yang, G., Huang, X., Hao, Z., Liu, M., Belongie, S.J., Hariharan, B.: PointFlow: 3D point cloud generation with continuous normalizing flows. In: ICCV, pp. 4540–4549 (2019)
Zhu, Z., et al.: NICE-SLAM: neural implicit scalable encoding for SLAM. In: CVPR, pp. 12776–12786 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hu, XQ., Wang, YP. (2024). QuadSampling: A Novel Sampling Method for Remote Implicit Neural 3D Reconstruction Based on Quad-Tree. In: Hu, SM., Cai, Y., Rosin, P. (eds) Computer-Aided Design and Computer Graphics. CADGraphics 2023. Lecture Notes in Computer Science, vol 14250. Springer, Singapore. https://doi.org/10.1007/978-981-99-9666-7_21
Download citation
DOI: https://doi.org/10.1007/978-981-99-9666-7_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-9665-0
Online ISBN: 978-981-99-9666-7
eBook Packages: Computer ScienceComputer Science (R0)