IP Library › Granted Patent US 12,374,043
Granted Patent B2
US 12,374,043 · App. 17/817,776 · Granted Jul 29, 2025

Utilizing machine learning models for patch retrieval and deformation in completing three-dimensional digital shapes

Inventors: Siddhartha Chaudhuri (Bangalore, IN); Bo Sun (Austin, TX); Vladimir Kim (Seattle, WA); Noam Aigerman (San Francisco, CA)
Assignee: Adobe Inc.
G06T17/20G06V10/22G06V10/754G06V2201/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,374,043
App. No.
17/817,776
Granted
Jul 29, 2025
Kind
B2
Abstract

Methods, systems, and non-transitory computer readable storage media are disclosed that utilizes machine learning models for patch retrieval and deformation in completing three-dimensional digital shapes. In particular, in one or more implementations the disclosed systems utilize a machine learning model to predict a coarse completion shape from an incomplete 3D digital shape. The disclosed systems sample coarse 3D patches from the coarse 3D digital shape and learn a shape distance function to retrieve detailed 3D shape patches in the input shape. Moreover, the disclosed systems learn a deformation for each retrieved patch and blending weights to integrate the retrieved patches into a continuous surface.

Claims (61)

1. A computer-implemented method comprising:

generating, utilizing a machine learning model, a coarse 3D digital shape from an incomplete 3D digital shape;

sampling a plurality of coarse 3D patches from the coarse 3D digital shape from within a plurality of patch regions across the coarse 3D digital shape;

retrieving, for the plurality of patch regions, a plurality of candidate 3D patches from the incomplete 3D digital shape based on the plurality of coarse 3D patches by, for a first patch region of the plurality of patch regions:

generating geometric similarity measures between a first coarse 3D patch of the plurality of coarse 3D patches from the coarse 3D digital shape and a plurality of 3D patches from across the incomplete 3D digital shape; and

selecting a candidate 3D patch of the plurality of candidate 3D patches utilizing the geometric similarity measures; and

generating a complete 3D shape by combining the plurality of candidate 3D patches for the plurality of patch regions.

2. The computer-implemented method of claim 1 , further comprising, for a patch region of the plurality of patch regions:

determining a set of candidate 3D patches for a sub-volume from the plurality of candidate 3D patches for the plurality of patch regions;

generating a transformed 3D sub-volume by blending the set of candidate 3D patches for the sub-volume; and

generating the complete 3D shape utilizing the transformed 3D sub-volume.

3. The computer-implemented method of claim 2 , wherein generating the transformed 3D sub-volume comprises:

generating, utilizing a blending-deformation machine learning model, blending weights and transformations corresponding to the set of candidate 3D patches; and

blending the plurality of candidate 3D patches utilizing the blending weights and the transformations.

4. The computer-implemented method of claim 3 , wherein blending the plurality of candidate 3D patches further comprises:

applying the transformations to the plurality of candidate 3D patches to generate transformed candidate 3D patches; and

combining the transformed candidate 3D patches utilizing the blending weights.

5. The computer-implemented method of claim 1 , wherein generating the coarse 3D digital shape comprises utilizing a convolutional neural network to generate the coarse 3D digital shape, and wherein the coarse 3D digital shape has a lower resolution than the incomplete 3D digital shape.

6. The computer-implemented method of claim 1 , wherein generating the geometric similarity measures comprises:

generating, utilizing a first encoder, a coarse 3D patch encoding from the first coarse 3D patch;

generating, utilizing a second encoder, a plurality of 3D patch encodings from the plurality of 3D patches; and

comparing the coarse 3D patch encoding and the plurality of 3D patch encodings to determine the geometric similarity measures.

7. The computer-implemented method of claim 6 , wherein comparing the coarse 3D patch encoding and the plurality of 3D patch encodings comprises determining distances between the coarse 3D patch encoding and the plurality of 3D patch encodings within a feature space.

8. The computer-implemented method of claim 6 , further comprising training the first encoder and the second encoder utilizing a first 3D sample and a second 3D sample by:

determining a geometric distance agnostic to transformations by analyzing distance metrics across combinations of transformations of the first 3D sample and the second 3D sample; and

modifying parameters of the first encoder and the second encoder by comparing an embedding distance between the first 3D sample and the second 3D sample in a feature space to the geometric distance.

9. A system comprising:

one or more computer memory devices; and

one or more processing devices configured to cause the system to:

generate, utilizing a machine learning model, a coarse 3D digital shape from an incomplete 3D digital shape;

sampling a plurality of coarse 3D patches from the coarse 3D digital shape from within a plurality of patch regions across the coarse 3D digital shape;

retrieving, for the plurality of patch regions, a plurality of candidate 3D patches from the incomplete 3D digital shape based on the plurality of coarse 3D patches by, for a first patch region of the plurality of patch regions:

generating geometric similarity measures between a first coarse 3D patch of the plurality of coarse 3D patches from the coarse 3D digital shape and a plurality of 3D patches from across the incomplete 3D digital shape; and

selecting a candidate 3D patch of the plurality of candidate 3D patches utilizing the geometric similarity measures; and

generate a complete 3D shape by blending the plurality of candidate 3D patches for the plurality of patch regions.

10. The system of claim 9 , wherein the one or more processing devices are further configured to, for a patch region:

generate, utilizing a blending-deformation neural network, blending weights corresponding to a set of candidate 3D patches for the patch region;

generate, utilizing the blending-deformation neural network, transformations corresponding to the set of candidate 3D patches for the patch region; and

blend the plurality of candidate 3D patches for the patch region utilizing the blending weights and the transformations.

11. The system of claim 10 , wherein the one or more processing devices are further configured to train the blending-deformation neural network utilizing a reconstruction loss and a smoothness loss.

12. The system of claim 9 , wherein the incomplete 3D digital shape has a first resolution and the one or more processing devices are further configured to cause the system to generate the coarse 3D digital shape utilizing the machine learning model by utilizing a convolutional neural network to generate a 3D shape having a second resolution lower than the first resolution.

13. The system of claim 9 , wherein the one or more processing devices are further configured to generate the geometric similarity measures by:

generating, utilizing one or more encoders, a coarse 3D patch encoding in a feature space from the first coarse 3D patch; and

generating, utilizing the one or more encoders, a plurality of 3D patch encodings in the feature space from the plurality of 3D patches.

14. The system of claim 13 , wherein the one or more processing devices are further configured to generate the geometric similarity measures based on distances between the coarse 3D patch encoding and the plurality of 3D patch encodings within the feature space.

15. A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

generating, utilizing a convolutional neural network, a coarse 3D digital shape from an incomplete 3D digital shape;

extracting a plurality of candidate 3D patches corresponding to a plurality of coarse 3D patches sampled from across the coarse 3D digital shape by:

generating, utilizing an encoder, candidate 3D patch encodings from the plurality of candidate 3D patches and a candidate coarse 3D patch encoding from the plurality of coarse 3D patches; and

comparing distances between the candidate 3D patch encodings and the candidate coarse 3D patch encoding; and

generating a complete 3D shape by determining transformations and blending weights for the plurality of candidate 3D patches.

16. The non-transitory computer readable medium of claim 15 , wherein generating the complete 3D shape comprises applying the transformations to the plurality of candidate 3D patches to generate transformed candidate 3D patches.

17. The non-transitory computer readable medium of claim 16 , wherein generating the complete 3D shape comprises blending the transformed candidate 3D patches utilizing the blending weights.

18. The non-transitory computer readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:

determining an additional coarse 3D patch from the coarse 3D digital shape;

retrieving an additional plurality of candidate 3D patches based on the additional coarse 3D patch; and

generating the complete 3D shape utilizing the plurality of candidate 3D patches and the additional plurality of candidate 3D patches.

19. The non-transitory computer readable medium of claim 18 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:

generating a first 3D sub-volume by blending the plurality of candidate 3D patches utilizing a first set of transformations and a first set of blending weights; and

generating a second 3D sub-volume by blending the additional plurality of candidate 3D patches utilizing a second set of transformations and a second set of blending weights.

20. The non-transitory computer readable medium of claim 19 , wherein generating the complete 3D shape comprises combining the first 3D sub-volume and the second 3D sub-volume.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 5, 2022
From: CHAUDHURI, SIDDHARTHA; SUN, BO; KIM, VLADIMIR; AIGERMAN, NOAM
To: ADOBE INC.
Reel/Frame 060732/0988 →
Continuity (1)
Related Publication 20240046567A1 · Feb 8, 2024
References Cited (88)
US 11334971B2 · Lin · 2022 [cited by examiner]
US 11587291B2 · Wang · 2023 [cited by examiner]
US 11836860B2 · Chandran · 2023 [cited by examiner]
US 20200250540A1 · Mehr · 2020 [cited by examiner]
US 20200327675A1 · Lin · 2020 [cited by examiner]
US 20210350620A1 · Bronstein · 2021 [cited by examiner]
US 20220005212A1 · Nagano · 2022 [cited by examiner]
US 20220392162A1 · Shen · 2022 [cited by examiner]
CN 113379646B · 2022 [cited by examiner]
2017 Han, Xiaoguang, et al. “High-resolution shape completion using deep neural networks for global structure and local geometry inference.” Proceedings of the IEEE international conference on computer vision. 2017. (Ye… [cited by examiner]
2020 Peng, Yanjun, et al. “Sparse-to-dense multi-encoder shape completion of unstructured point cloud.” IEEE Access 8 (2020): 30969-30978. (Year: 2020). [cited by examiner]
2020 Li, Guoyan, et al. “N-DPC: Dense 3D point cloud completion based on improved multi-stage network.” Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition. 2020. (Year: 2020). [cited by examiner]
2021 Chu, Lei, Hao Pan, and Wenping Wang. “Unsupervised shape completion via deep prior in the neural tangent kernel perspective.” ACM Transactions on Graphics (TOG) 40.3 (2021): 1-17. (Year: 2021). [cited by examiner]
Alliegro, Antonio, et al. “Denoise and contrast for category agnostic shape completion.” Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021. (Year: 2021). [cited by examiner]
2021 Shi, Jieqi, et al. “Graph-guided deformation for point cloud completion.” IEEE Robotics and Automation Letters 6.4 (2021): 7081-7088. (Year: 2021). [cited by examiner]
Liu, Ran et al. “Hole-filling Based on Disparity Map and Inpainting for Depth-Image-Based Rendering;” 2016; International Journal of Hybrid Information Technology, vol. 9, No. 5 (2016); pp. 145-164 (Year: 2016). [cited by examiner]
Dragomir Anguelov, Praveen Srinivasan, Daphne Koller, Sebastian Thrun, Jim Rodgers, and James Davis. SCAPE: Shape completion and animation of people. ACM Transac-tions on Graphics (TOG), 24:408-416, Jul. 2005. [cited by applicant]
Connelly Barnes, Eli Shechtman, Adam Finkelstein, and Dan B Goldman. Patch Match: A randomized correspondence algorithm for structural image editing. ACM Transactions on Graphics (Proc. SIGGRAPH), 28(3), Aug. 2009. [cited by applicant]
Paul J. Besl and Neil D. McKay. A method for registration of 3-d shapes. IEEE Trans. Pattern Anal. Mach. Intell., 14(2):239-256, 1992. [cited by applicant]
Volker Blanz and Thomas Vetter. A morphable model for the synthesis of 3d faces. In Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH '99, p. 187-194, USA, 1999. ACM Pre… [cited by applicant]
Rohan Chabra, Jan E. Lenssen, Eddy Ilg, Tanner Schmidt, Julian Straub, Steven Lovegrove, and Richard Newcombe. Deep local shapes: Learning local sdf priors for detailed 3d reconstruction. In ECCV, 2020. [cited by applicant]
Angel X. Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, Jianxiong Xiao, Li Yi, and Fisher Yu. ShapeNet: An Information-Rich 3D Model … [cited by applicant]
Siddhartha Chaudhuri and Vladlen Koltun. Data-driven suggestions for creativity support in 3d modeling. ACM Transactions on Graphics, 29, 12 2010. [cited by applicant]
Zhiqin Chen, Vladimir G. Kim, Matthew Fisher, Noam Aigerman, Hao Zhang, and Siddhartha Chaudhuri. Decorgan: 3d shape detailization by conditional refinement. Proceedings of IEEE Conference on Computer Vision and Pattern… [cited by applicant]
Zhang Chen, Yinda Zhang, Kyle Genova, Sean Fanello, Sofien Bouaziz, Christian Hane, Ruofei Du, Cem Keskin, Thomas Funkhouser, and Danhang Tang. Multiresolution deep implicit functions for 3d shape representation. In ICC… [cited by applicant]
Brian Curless and Marc Levoy. A volumetric method for building complex models from range images. In Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH '96, p. 303-312, Ne… [cited by applicant]
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, and Matthias Nießner. Scannet: Richly-annotated 3d reconstructions of indoor scenes. In Proc. Computer Vision and Pattern Recognition (CVPR), … [cited by applicant]
Angela Dai, Charles Ruizhongtai Qi, and Matthias Nießner. Shape completion using 3d-encoder-predictor cnns and shape synthesis. In Proc. Computer Vision and Pattern Recognition (CVPR), IEEE, 2017. [cited by applicant]
James Davis, S.R. Marschner, Matt Garr, and Marc Levoy. Filling holes in complex surfaces using volumetric diffusion. pp. 428-441, Feb. 2002. [cited by applicant]
Alexei A. Efros and Thomas K. Leung. Texture synthesis by non-parametric sampling. In IEEE International Conference on Computer Vision (ICCV), 1999. [cited by applicant]
Kyle Genova, Forrester Cole, Avneesh Sud, Aaron Sarna, and Thomas Funkhouser. Local deep implicit functions for 3d shape. InCVPR, 2019. [cited by applicant]
Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan Russell, and Mathieu Aubry. AtlasNet: A Papier-Mache Approach to Learning 3D Surface Generation. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognit… [cited by applicant]
Xiaoyuan Guo, Jun Xiao, and Ying Wang. A survey on algorithms of hole filling in 3d surface reconstruction.The Visual Computer, 34, Jan. 2018. [cited by applicant]
X. Han, Z. Li, H. Huang, E. Kalogerakis, and Y. Yu. High-resolution shape completion using deep neural networks for global structure and local geometry inference. In IEEE International Conference on Computer Vision (ICC… [cited by applicant]
Rana Hanocka, Amir Hertz, Noa Fish, Raja Giryes, Shachar Fleishman, and Daniel Cohen-Or. Meshcnn: A network with an edge.ACM Trans. Graph., 38(4), Jul. 2019. [cited by applicant]
Rana Hanocka, Gal Metzer, Raja Giryes, and Daniel Cohen-Or. Point2mesh: A self-prior for deformable meshes.ACM Trans. Graph., 39(4), Jul. 2020. [cited by applicant]
James Hays and Alexei A Efros. Scene completion using millions of photographs.ACM Transactions on Graphics (SIGGRAPH 2007), 26(3), 2007. [cited by applicant]
Amir Hertz, Rana Hanocka, Raja Giryes, and Daniel Cohen-Or. Deep geometric texture synthesis.ACM Trans. Graph., 39(4), 2020. [cited by applicant]
Ping Hu, Changsheng Wang, Baojun Li, and Mingzeng Liu. Filling holes in triangular meshes in engineering. JSW, 7:141-148, Jan. 2012. [cited by applicant]
Zitian Huang, Yikuan Yu, Jiawen Xu, Feng Ni, and Xinyi Le. Pf-net: Point fractal network for 3d point cloud completion. In CVPR, 2020. [cited by applicant]
Angjoo Kanazawa, Michael J. Black, David W. Jacobs, and Jitendra Malik. End-to-end recovery of human shape and pose. In2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA,… [cited by applicant]
M. Kazhdan, M. Bolitho, and H. Hoppe. Poisson surface reconstruction. In Proceedings of the fourth Eurographics symposium on Geometry processing, 2005. [cited by applicant]
M. Kazhdan and H. Hoppe. Screened poisson surface reconstruction. InACM Transactions on Graphics (TOG), 2013. [cited by applicant]
Y. M. Kim, N. J. Mitra, D.-M. Yan, and L. Guibas. Acquiring 3d indoor environments with variability and repetition. In ACM Transactions on Graphics (TOG), 2012. [cited by applicant]
Nikos Kolotouros, Georgios Pavlakos, Michael J. Black, and Kostas Daniilidis. Learning to reconstruct 3d human pose and shape via model-fitting in the loop. In2019 IEEE/CVF International Conference on Computer Vision, I… [cited by applicant]
Vivek Kwatra, Arno Schodl, Irfan Essa, Greg Turk, and Aaron Bobick. Graphcut textures: Image and video synthesis using graph cuts. ACM Transactions on Graphics, SIG-GRAPH 2003, 22(3):277-286, Jul. 2003. [cited by applicant]
Marc Levoy, Kari Pulli, Brian Curless, Szymon Rusinkiewicz, David Koller, Lucas Pereira, Matt Ginzton, Sean Anderson, James Davis, Jeremy Ginsberg, Jonathan Shade, and Duane Fulk. The digital michelangelo project: 3d sc… [cited by applicant]
Dongping Li, Tianjia Shao, Hongzhi Wu, and Kun Zhou. Shape completion from a single rgbd image. In IEEE Transactions on Visualization & Computer Graphics, 2016. [cited by applicant]
Manyi Li and Hao Zhang. d2im-net: learning detail disentangled implicit fields from single images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10246-10255, Jun. 2021. [cited by applicant]
Y. Li, A. Dai, L. Guibas, and M. Nießner. Database-assisted object retrieval for real-time 3D reconstruction. In Computer Graphics Forum, 2015. [cited by applicant]
Yikang Li, Tao Ma, Yeqi Bai, Nan Duan, Sining Wei, and Xiaogang Wang. Pastegan: A semi-parametric method to generate image from scene graph. NeurIPS, 2019. [cited by applicant]
Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, and Michael J. Black. Smpl: A skinned multi-person linear model. ACM Trans. Graph., 34(6), Oct. 2015. [cited by applicant]
A. Nealen, T. Igarashi, O. Sorkine, and M. Alexa. Laplacian mesh optimization. In Proceedings of the 4th international conference on Computer graphics and interactive techniques, 2006. [cited by applicant]
Yutaka Ohtake, Alexander Belyaev, Marc Alexa, Greg Turk, and Hans-Peter Seidel. Multi-level partition of unity implicits. ACM Trans. Graph., 22(3):463-470, Jul. 2003. [cited by applicant]
Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang, Haiyu Zhao, Shuai Yi, and Ziwei Liu. Variational relational point completion network. arXiv preprint arXiv:2104.10154, 2021. [cited by applicant]
Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. Deepsdf: Learning continuous signed distance functions for shape representation. In The IEEE Conference on Computer Vision and Patt… [cited by applicant]
M. Pauly, N. J. Mitra, J. Giesen, M. H. Gross, and L. J. Guibas. Example-based 3d scan completion. In Symposium on Geometry Processing, 2005. [cited by applicant]
Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, and Michael J. Black. Expressive body capture: 3d hands, face, and body from a single image. In IEEE Conference on… [cited by applicant]
Songyou Peng, Michael Niemeyer, Lars Mescheder, Marc Pollefeys, and Andreas Geiger. Convolutional occupancy networks. In European Conference on Computer Vision (ECCV), 2020. [cited by applicant]
Xiaojuan Qi, Qifeng Chen, Jiaya Jia, and Vladlen Koltun. Semi-parametric image synthesis. InIn CVPR, 2018. [cited by applicant]
Anurag Ranjan, Timo Bolkart, Soubhik Sanyal, and Michael J. Black. Generating 3d faces using convolutional mesh autoencoders. In Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss, editors, Computer… [cited by applicant]
Yurui Ren, Xiaoming Yu, Ruonan Zhang, Thomas H. Li, Shan Liu, and Ge Li. Structureflow: Image inpainting via structure-aware appearance flow. In IEEE International Conference on Computer Vision (ICCV), 2019. [cited by applicant]
J. Rock, T. Gupta, J. Thorsen, J. Gwak, D. Shin, and D. Hoiem. Completing 3d object shape from one depth image. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [cited by applicant]
Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015. [cited by applicant]
O. Sorkine and D. Cohen-Or. Least-squares meshes. In Shape Modeling Applications, 2004. [cited by applicant]
M. Sung, V. G. Kim, R. Angst, and L. Guibas. Data-driven structural priors for shape completion. In ACM Transactions on Graphics (TOG), 2015. [cited by applicant]
Kenshi Takayama, Ryan Schmidt, Karan Singh, Takeo Igarashi, Tamy Boubekeur, and Olga Sorkine-Hornung. Geobrush: Interactive mesh geometry cloning.Computer Graphics Forum (Proc. Eurographics 2011), 30(2):613-622, 2011. [cited by applicant]
Lyne P Tchapmi, Vineet Kosaraju, S. Hamid Rezatofighi, Ian Reid, and Silvio Savarese. Topnet: Structural point cloud decoder. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [cited by applicant]
Hung-Yu Tseng, Hsin-Ying Lee, Lu Jiang, Ming-Hsuan Yang, and Weilong Yang. Retrievegan: Image synthesis via differentiable patch retrieval. InIn ECCV, 2020. [cited by applicant]
Greg Turk and Marc Levoy. Zippered polygon meshes from range images. In Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH '94, p. 311-318, New York, NY, USA, 1994. Assoc… [cited by applicant]
Dmitry Ulyanov, Andrea Vedaldi, and Victor S. Lempitsky. Deep image prior. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, Jun. 18-22, 2018, pp. 9446-9454. Compute… [cited by applicant]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vi… [cited by applicant]
Xiaogang Wang, Marcelo H. Ang Jr., and Gim Hee Lee. Cascaded refinement network for point cloud completion. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2020. [cited by applicant]
Xiaogang Wang, Marcelo H. Ang Jr., and Gim Hee Lee. Voxel-based network for shape completion by leveraging edge generation. In ICCV), 2021. [cited by applicant]
Mark Wheeler, Yoichi Sato, and Katsushi Ikeuchi. Consensus surfaces for modeling 3d objects from multiple range images. pp. 917-924, Feb. 1998. [cited by applicant]
Jiajun Wu, Chengkai Zhang, Tianfan Xue, William T Freeman, and Joshua B Tenenbaum. Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. In Advances in Neural Information Process… [cited by applicant]
Z. Wu, S. Song, A. Khosla, F. Yu, L. Zhang, X. Tang, and J. Xiao. 3d shapenets: A deep representation for volumetric shape modeling. In Proceedings of 28th IEEE Conference on Computer Vision and Pattern Recognition (CVP… [cited by applicant]
Peng Xiang, Xin Wen, Yu-Shen Liu, Yan-Pei Cao, Pengfei Wan, Wen Zheng, and Zhizhong Han. Snowflakenet: Point cloud completion by snowflake point deconvolution with skip-transformer. In ICCV, 2021. [cited by applicant]
Chulin Xie, Chuxin Wang, Bo Zhang, Hao Yang, Dong Chen, and Fang Wen. Style-based point generator with adversarial rendering for point cloud completion. In Proceedings of the IEEE/CVF Conference on Computer Vision and P… [cited by applicant]
Haozhe Xie, Hongxun Yao, Shangchen Zhou, Jiageng Mao, Shengping Zhang, and Wenxiu Sun. Grnet: Gridding residual network for dense point cloud completion. In ECCV, 2020. [cited by applicant]
Xuehan Xiong and Fernando De la Torre. Supervised descent method and its applications to face alignment. pp. 532-539, Jun. 2013. [cited by applicant]
Rui Xu, Minghao Guo, Jiaqi Wang, Xiaoxiao Li, Bolei Zhou, and Chen Change Loy. Texture memory-augmented deep patch-based image inpainting. In IEEE Transactions on Image Processing (TIP), 2021. [cited by applicant]
Fuzhi Yang, Huan Yang, Jianlong Fu, Hongtao Lu, and Baining Guo. Learning texture transformer network for image super-resolution. In CVPR, Jun. 2020. [cited by applicant]
Xumin Yu, Yongming Rao, Ziyi Wang, Zuyan Liu, Jiwen Lu, and Jie Zhou. Pointr: Diverse point cloud completion with geometry-aware transformers. In ICCV, 2021. [cited by applicant]
Wentao Yuan, Tejas Khot, David Held, Christoph Mertz, and Martial Hebert. Pon: Point completion network. In 3D Vision (3DV), 2018 International Conference on 3D Vision, 2018. [cited by applicant]
Wenxiao Zhang, Qingan Yan, and Chunxia Xiao. Detail preserved point cloud completion via separated feature aggregation. In ECCV, 2020. [cited by applicant]
W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld. Face recognition: A literature survey. ACM Comput. Surv., 35(4):399-458, Dec. 2003. [cited by applicant]
Kun Zhou, Xin Huang, Xi Wang, Yiying Tong, Mathieu Desbrun, Baining Guo, and Heung-Yeung Shum. Mesh quilting for geometric texture synthesis. In ACM SIGGRAPH 2006 Papers, SIGGRAPH '06, p. 690-697, 2006. [cited by applicant]