Abstract
In recent years, neural implicit representations have made remarkable progress in modeling of 3D shapes with arbitrary topology. In this work, we address two key limitations of such representations, in failing to capture local 3D geometric fine details, and to learn from and generalize to shapes with unseen 3D transformations. To this end, we introduce a novel family of graph implicit functions with equivariant layers that facilitates modeling fine local details and guaranteed robustness to various groups of geometric transformations, through local k-NN graph embeddings with sparse point set observations at multiple resolutions. Our method improves over the existing rotation-equivariant implicit function from 0.69 to 0.89 (IoU) on the ShapeNet reconstruction task. We also show that our equivariant implicit function can be extended to other types of similarity transformations and generalizes to unseen translations and scaling.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Atzmon, M., Haim, N., Yariv, L., Israelov, O., Maron, H., Lipman, Y.: Controlling neural level sets. arXiv preprint arXiv:1905.11911 (2019)
Atzmon, M., Lipman, Y.: SAL: sign agnostic learning of shapes from raw data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2565–2574 (2020)
Atzmon, M., Lipman, Y.: SAL++: sign agnostic learning with derivatives. arXiv preprint arXiv:2006.05400 (2020)
Bautista, M.A., Talbott, W., Zhai, S., Srivastava, N., Susskind, J.M.: On the generalization of learning-based 3D reconstruction. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2180–2189 (2021)
Chabra, R., et al.: Deep local shapes: learning local SDF priors for detailed 3D reconstruction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 608–625. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58526-6_36
Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)
Chatzipantazis, E., Pertigkiozoglou, S., Dobriban, E., Daniilidis, K.: SE(3)-equivariant attention networks for shape reconstruction in function space. arXiv preprint arXiv:2204.02394 (2022)
Chen, Y., Fernando, B., Bilen, H., Mensink, T., Gavves, E.: Neural feature matching in implicit 3D representations. In: International Conference on Machine Learning, pp. 1582–1593. PMLR (2021)
Chen, Y., et al.: PointMixup: augmentation for point clouds. arXiv preprint arXiv:2008.06374 (2020)
Chen, Z., Zhang, H.: Learning implicit fields for generative shape modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5939–5948 (2019)
Chibane, J., Alldieck, T., Pons-Moll, G.: Implicit functions in feature space for 3D shape reconstruction and completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6970–6981 (2020)
Choy, C.B., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. arXiv preprint arXiv:1606.03558 (2016)
Cohen, T., Welling, M.: Group equivariant convolutional networks. In: International Conference on Machine Learning, pp. 2990–2999. PMLR (2016)
Cohen, T.S., Welling, M.: Steerable CNNs. arXiv preprint arXiv:1612.08498 (2016)
Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828–5839 (2017)
Davies, T., Nowrouzezahrai, D., Jacobson, A.: On the effectiveness of weight-encoded neural implicit 3D shapes. arXiv preprint arXiv:2009.09808 (2020)
Deng, C., Litany, O., Duan, Y., Poulenard, A., Tagliasacchi, A., Guibas, L.: Vector neurons: a general framework for SO(3)-equivariant networks. arXiv preprint arXiv:2104.12229 (2021)
Erler, P., Guerrero, P., Ohrhallinger, S., Mitra, N.J., Wimmer, M.: Points2Surf learning implicit surfaces from point clouds. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 108–124. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_7
Fuchs, F., Worrall, D., Fischer, V., Welling, M.: SE(3)-transformers: 3D roto-translation equivariant attention networks. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Fujiwara, K., Hashimoto, T.: Neural implicit embedding for point cloud analysis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11734–11743 (2020)
Genova, K., Cole, F., Sud, A., Sarna, A., Funkhouser, T.: Deep structured implicit functions. arXiv preprint arXiv:1912.06126 (2019)
Genova, K., Cole, F., Sud, A., Sarna, A., Funkhouser, T.: Local deep implicit functions for 3D shape. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4857–4866 (2020)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: International Conference on Machine Learning, pp. 1263–1272. PMLR (2017)
Hanocka, R., Hertz, A., Fish, N., Giryes, R., Fleishman, S., Cohen-Or, D.: MeshCNN: a network with an edge. ACM Trans. Graph. (TOG) 38(4), 1–12 (2019)
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)
Jiang, Y., Ji, D., Han, Z., Zwicker, M.: SDFDiff: differentiable rendering of signed distance fields for 3D shape optimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1251–1261 (2020)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Li, J., Chen, B.M., Lee, G.H.: SO-Net: self-organizing network for point cloud analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9397–9406 (2018)
Liu, S., Saito, S., Chen, W., Li, H.: Learning to infer implicit surfaces without 3D supervision. In: Advances in Neural Information Processing Systems, pp. 8295–8306 (2019)
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)
Niemeyer, M., Mescheder, L., Oechsle, M., Geiger, A.: Differentiable volumetric rendering: learning implicit 3D representations without 3D supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3504–3515 (2020)
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)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)
Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.: Convolutional occupancy networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 523–540. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_31
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
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
Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: PIFu: pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2304–2314 (2019)
Satorras, V.G., Hoogeboom, E., Welling, M.: E(n) equivariant graph neural networks. arXiv preprint arXiv:2102.09844 (2021)
Shen, W., Zhang, B., Huang, S., Wei, Z., Zhang, Q.: 3D-rotation-equivariant quaternion neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 531–547. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_32
Simeonov, A., et al.: Neural descriptor fields: SE(3)-equivariant object representations for manipulation. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 6394–6400. IEEE (2022)
Sitzmann, V., Chan, E., Tucker, R., Snavely, N., Wetzstein, G.: MetaSDF: meta-learning signed distance functions. In: Advances in Neural Information Processing Systems, vol. 33, pp. 10136–10147 (2020)
Sosnovik, I., Szmaja, M., Smeulders, A.: Scale-equivariant steerable networks. In: International Conference on Learning Representations (2019)
Takikawa, T., et al.: Neural geometric level of detail: real-time rendering with implicit 3D shapes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11358–11367 (2021)
Tang, J.H., et al.: OctField: hierarchical implicit functions for 3D modeling. In: Advances in Neural Information Processing Systems, vol. 34, pp. 12648–12660 (2021)
Thomas, N., et al.: Tensor field networks: rotation-and translation-equivariant neural networks for 3D point clouds. arXiv preprint arXiv:1802.08219 (2018)
Wang, P.S., Liu, Y., Tong, X.: Dual octree graph networks for learning adaptive volumetric shape representations. arXiv preprint arXiv:2205.02825 (2022)
Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. (TOG) 38(5), 1–12 (2019)
Weiler, M., Geiger, M., Welling, M., Boomsma, W., Cohen, T.: 3D steerable CNNs: learning rotationally equivariant features in volumetric data. In: NeurIPS (2018)
Weiler, M., Hamprecht, F.A., Storath, M.: Learning steerable filters for rotation equivariant CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 849–858 (2018)
Worrall, D.E., Garbin, S.J., Turmukhambetov, D., Brostow, G.J.: Harmonic networks: deep translation and rotation equivariance. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5028–5037 (2017)
Xu, Q., Wang, W., Ceylan, D., Mech, R., Neumann, U.: DISN: deep implicit surface network for high-quality single-view 3D reconstruction. In: Advances in Neural Information Processing Systems, pp. 492–502 (2019)
Xu, Y., Fan, T., Yuan, Y., Singh, G.: Ladybird: Quasi-Monte Carlo sampling for deep implicit field based 3D reconstruction with symmetry. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 248–263. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_15
Yuan, Y., Nüchter, A.: An algorithm for the SE(3)-transformation on neural implicit maps for remapping functions. IEEE Robot. Autom. Lett. 7, 7763–7770 (2022)
Zaheer, M., Kottur, S., Ravanbakhsh, S., Poczos, B., Salakhutdinov, R., Smola, A.: Deep sets. arXiv preprint arXiv:1703.06114 (2017)
Zhu, W., Qiu, Q., Calderbank, R., Sapiro, G., Cheng, X.: Scale-equivariant neural networks with decomposed convolutional filters. arXiv preprint arXiv:1909.11193 (2019)
Acknowledgement
This research was supported in part by SAVI/MediFor project, ERC Starting Grant Scan2CAD (804724), EPSRC programme grant Visual AI EP/T028572/1, and National Research Foundation Singapore and DSO National Laboratories under its AI Singapore Programme (AISG Award No: AISG2-RP-2020-016). We thank Angela Dai for the video voice over.
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
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, Y., Fernando, B., Bilen, H., Nießner, M., Gavves, E. (2022). 3D Equivariant Graph Implicit Functions. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13663. Springer, Cham. https://doi.org/10.1007/978-3-031-20062-5_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-20062-5_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20061-8
Online ISBN: 978-3-031-20062-5
eBook Packages: Computer ScienceComputer Science (R0)