Abstract
Recently, studies considering domain gaps in shape completion attracted more attention, due to the undesirable performance of supervised methods on real scans. They only noticed the gap in input scans, but ignored the gap in output prediction, which is specific for completion. In this paper, we disentangle partial scans into three (domain, shape, and occlusion) factors to handle the output gap in cross-domain completion. For factor learning, we design view-point prediction and domain classification tasks in a self-supervised manner and bring a factor permutation consistency regularization to ensure factor independence. Thus, scans can be completed by simply manipulating occlusion factors while preserving domain and shape information. To further adapt to instances in the target domain, we introduce an optimization stage to maximize the consistency between completed shapes and input scans. Extensive experiments on real scans and synthetic datasets show that ours outperforms previous methods by a large margin and is encouraging for the following works. Code is available at https://github.com/azuki-miho/OptDE.
J. Gong and F. Liu—Equal Contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aberman, K., Li, P., Lischinski, D., Sorkine-Hornung, O., Cohen-Or, D., Chen, B.: Skeleton-aware networks for deep motion retargeting. ACM Trans. Graph. (TOG) 39(4), 62-1 (2020)
Barlow, H.B., Kaushal, T.P., Mitchison, G.J.: Finding minimum entropy codes. Neural Comput. 1(3), 412–423 (1989)
Bau, D., et al.: Semantic photo manipulation with a generative image prior. In: SIGGRAPH (2020)
Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: 2017 International Conference on 3D Vision (3DV), pp. 667–676. IEEE Computer Society (2017)
Chang, A.X., et al.: ShapeNet: an information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)
Chen, X., Chen, B., Mitra, N.J.: Unpaired point cloud completion on real scans using adversarial training. In: International Conference on Learning Representations (2020)
Cosmo, L., Norelli, A., Halimi, O., Kimmel, R., Rodolà, E.: LIMP: learning latent shape representations with metric preservation priors. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 19–35. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_2
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)
Fu, H., et al.: 3d-future: 3d furniture shape with texture. arXiv preprint arXiv:2009.09633 (2020)
Fumero, M., Cosmo, L., Melzi, S., Rodolà, E.: Learning disentangled representations via product manifold projection. In: ICML (2021)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning, pp. 1180–1189. PMLR (2015)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The Kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361. IEEE (2012)
Gonzalez-Garcia, A., van de Weijer, J., Bengio, Y.: Image-to-image translation for cross-domain disentanglement. In: NeurIPS (2018)
Hou, J., Dai, A., Nießner, M.: RevealNet: seeing behind objects in RGB-D scans. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2098–2107 (2020)
Huang, Z., Yu, Y., Xu, J., Ni, F., Le, X.: PF-Net: point fractal network for 3d point cloud completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7662–7670 (2020)
Kim, H., Mnih, A.: Disentangling by factorising. In: International Conference on Machine Learning (ICML), pp. 2649–2658. PMLR (2018)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)
Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3d human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2252–2261 (2019)
Liu, A.H., Liu, Y.C., Yeh, Y.Y., Wang, Y.C.F.: A unified feature disentangler for multi-domain image translation and manipulation. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 2595–2604 (2018)
Liu, M., Sheng, L., Yang, S., Shao, J., Hu, S.M.: Morphing and sampling network for dense point cloud completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11596–11603 (2020)
Liu, Y.C., Yeh, Y.Y., Fu, T.C., Wang, S.D., Chiu, W.C., Wang, Y.C.F.: Detach and adapt: learning cross-domain disentangled deep representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8867–8876 (2018)
Ma, F., Ayaz, U., Karaman, S.: Invertibility of convolutional generative networks from partial measurements. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Pan, L., et al.: Variational relational point completion network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8524–8533 (2021)
Peng, X., Huang, Z., Sun, X., Saenko, K.: Domain agnostic learning with disentangled representations. In: International Conference on Machine Learning, pp. 5102–5112. PMLR (2019)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3d classification and segmentation. In: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 652–660 (2017)
Schmidhuber, J.: Learning factorial codes by predictability minimization. Neural Comput. 4(6), 863–879 (1992)
Shu, D.W., Park, S.W., Kwon, J.: 3d point cloud generative adversarial network based on tree structured graph convolutions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3859–3868 (2019)
Sigal, L., Balan, A., Black, M.: Combined discriminative and generative articulated pose and non-rigid shape estimation. Adv. Neural. Inf. Process. Syst. 20, 1337–1344 (2007)
Straßer, W.: Schnelle kurven-und flächendarstellung auf grafischen sichtgeräten. Ph.D. thesis (1974)
Tchapmi, L.P., Kosaraju, V., Rezatofighi, H., Reid, I., Savarese, S.: TopNet: structural point cloud decoder. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 383–392 (2019)
Wang, H., Liu, Q., Yue, X., Lasenby, J., Kusner, M.J.: Unsupervised point cloud pre-training via occlusion completion. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9782–9792 (2021)
Wang, X., Ang Jr, M.H., Lee, G.H.: Cascaded refinement network for point cloud completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 790–799 (2020)
Wen, X., Han, Z., Cao, Y.P., Wan, P., Zheng, W., Liu, Y.S.: Cycle4completion: unpaired point cloud completion using cycle transformation with missing region coding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13080–13089 (2021)
Wen, X., Li, T., Han, Z., Liu, Y.S.: Point cloud completion by skip-attention network with hierarchical folding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1939–1948 (2020)
Wen, X., et al.: PMP-Net: point cloud completion by learning multi-step point moving paths. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7443–7452 (2021)
Wu, R., Chen, X., Zhuang, Y., Chen, B.: Multimodal shape completion via conditional generative adversarial networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 281–296. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_17
Wu, X., Huang, H., Patel, V.M., He, R., Sun, Z.: Disentangled variational representation for heterogeneous face recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 9005–9012 (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)
Xie, H., Yao, H., Zhou, S., Mao, J., Zhang, S., Sun, W.: GRNet: gridding residual network for dense point cloud completion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 365–381. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_21
Yang, Y., Feng, C., Shen, Y., Tian, D.: FoldingNet: point cloud auto-encoder via deep grid deformation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 206–215 (2018)
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)
Zhang, J., et al.: Unsupervised 3d shape completion through GAN inversion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1768–1777 (2021)
Zhang, W., Yan, Q., Xiao, C.: Detail preserved point cloud completion via separated feature aggregation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 512–528. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58595-2_31
Acknowledgments
This work is sponsored by the National Key Research and Development Program of China (No. 2019YFC1521104), the National Natural Science Foundation of China (No. 61972157,72192821), Shanghai Municipal Science and Technology Major Project (2021SHZDZX0102), Shanghai Sailing Program (22YF1420300), Shanghai Science and Technology Commission (21511101200) and SenseTime Collaborative Research Grant.
Author information
Authors and Affiliations
Corresponding authors
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
Gong, J. et al. (2022). Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation. 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 13662. Springer, Cham. https://doi.org/10.1007/978-3-031-20086-1_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-20086-1_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20085-4
Online ISBN: 978-3-031-20086-1
eBook Packages: Computer ScienceComputer Science (R0)