AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
Neural Distance Fields can represent a larger class of shapes including open surfaces, shapes with inner structures, as well as curves, manifold data and analytical mathematical functions

Neural Unsigned Distance Fields for Implicit Function Learning

NIPS 2020, (2020)

Cited by: 0|Views39
EI
Full Text
Bibtex
Weibo

Abstract

In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in resolution, and ability to represent diverse topologies. However, neural implicit representations are limi...More

Code:

Data:

0
Introduction
  • Reconstructing continuous and renderable surfaces from unstructured and incomplete 3D point-clouds is a fundamental problem in robotics, vision and graphics.
  • Many real world objects such as cars, cylinders, or a wall of a scanned 3D scene can not be represented.
  • This is a barrier, both in terms of tedious data pre-processing — surfaces need to be closed which often leads to artifacts and loss of detail — and more importantly the ability to output open surfaces
Highlights
  • Reconstructing continuous and renderable surfaces from unstructured and incomplete 3D point-clouds is a fundamental problem in robotics, vision and graphics
  • We have shown how a simple change in the representation, from occupancy or signed distances to unsigned distances, significantly broadens the scope of current implicit function learning approaches
  • Neural Distance Fields (NDF) can learn directly from real world scan data without need to artificially close the surfaces before training
  • More importantly, NDF can represent a larger class of shapes including open surfaces, shapes with inner structures, as well as curves, manifold data and analytical mathematical functions
  • We introduce algorithms to visualize NDF either efficiently projecting points to the surface, or directly rendering the field with a custom variant of sphere tracing
  • We believe that NDF are an important step towards the goal of finding a learnable output representation that allows continuous, high resolution outputs of arbitrary shape
Methods
  • 3.1 Background On Implicit Function Learning

    The first IFL papers for 3D shape representation learn a function, which given a vectorized shape code z ∈ Z, and a point p ∈ R3 predict an occupancy f (p, z) : R3 × Z → [0, 1] or a signed distance function f (p, z) : R3 × Z → R.
  • The authors' formulation of NDF predicts the unsigned distance field of surfaces, instead of relying on inside and outside.
  • This simple modification allows them to represent a much wider class of surfaces and manifolds, not necessarily closed.
  • The authors present algorithms which exploit NDF to visualize the reconstructed implicit surfaces as 1) dense point-clouds and meshes (Subsec.
Conclusion
  • The authors have shown how a simple change in the representation, from occupancy or signed distances to unsigned distances, significantly broadens the scope of current implicit function learning approaches.
  • The authors introduced NDF, a new method which has two main advantages w.r.t. to prior work.
  • NDF can learn directly from real world scan data without need to artificially close the surfaces before training.
  • More importantly, NDF can represent a larger class of shapes including open surfaces, shapes with inner structures, as well as curves, manifold data and analytical mathematical functions.
  • The authors believe that NDF are an important step towards the goal of finding a learnable output representation that allows continuous, high resolution outputs of arbitrary shape
Summary
  • Introduction:

    Reconstructing continuous and renderable surfaces from unstructured and incomplete 3D point-clouds is a fundamental problem in robotics, vision and graphics.
  • Many real world objects such as cars, cylinders, or a wall of a scanned 3D scene can not be represented.
  • This is a barrier, both in terms of tedious data pre-processing — surfaces need to be closed which often leads to artifacts and loss of detail — and more importantly the ability to output open surfaces
  • Methods:

    3.1 Background On Implicit Function Learning

    The first IFL papers for 3D shape representation learn a function, which given a vectorized shape code z ∈ Z, and a point p ∈ R3 predict an occupancy f (p, z) : R3 × Z → [0, 1] or a signed distance function f (p, z) : R3 × Z → R.
  • The authors' formulation of NDF predicts the unsigned distance field of surfaces, instead of relying on inside and outside.
  • This simple modification allows them to represent a much wider class of surfaces and manifolds, not necessarily closed.
  • The authors present algorithms which exploit NDF to visualize the reconstructed implicit surfaces as 1) dense point-clouds and meshes (Subsec.
  • Conclusion:

    The authors have shown how a simple change in the representation, from occupancy or signed distances to unsigned distances, significantly broadens the scope of current implicit function learning approaches.
  • The authors introduced NDF, a new method which has two main advantages w.r.t. to prior work.
  • NDF can learn directly from real world scan data without need to artificially close the surfaces before training.
  • More importantly, NDF can represent a larger class of shapes including open surfaces, shapes with inner structures, as well as curves, manifold data and analytical mathematical functions.
  • The authors believe that NDF are an important step towards the goal of finding a learnable output representation that allows continuous, high resolution outputs of arbitrary shape
Tables
  • Table1: Results of point cloud completion for closed and unprocessed cars from 10000 points and 3000 and 300 points. Chamfer-L2 results ×10−4. Left number shows the mean over Chamfer-L2 scores, right the median. Left Table: Results training on pre-processed closed meshes. Right Table: Results training on raw scans. NDF can represent closed surfaces equally well than SOTA (left), and obtain a significant boost in accuracy when trained on raw data (right), because they can learn the inner structures
Download tables as Excel
Related work
  • Distance fields can be found in computer vision, graphics, robotics and physics [37]. They are used for shape registration [26], model fitting [70, 2], to speed up inference in part based models [25], and for extracting skeletons and medial axis [22, 7]. However, to our knowledge, unsigned distance fields have not been used for learning 3D shapes. Here, we limit our discussion to learning based methods for 3D shape representation and reconstruction.

    2.1 Learning with Voxels, Meshes and Points-Clouds

    Since convolutions are natural on voxels, they have been the most popular representation for learning [39, 35, 65], but the memory footprint scales cubically with resolution, which has limited grids to small sizes of 323 [44, 83, 16, 75]. Higher resolutions (2563) [82, 81, 87] can be achieved at the cost of slow training, or difficult multi-resolution implementations [31, 72, 77]. Replacing occupancy with Truncated Signed Distance functions [17] for learning [19, 42, 66, 71] can reduce quantization artifacts, nonetheless TSDF values need to be stored in a grid of fixed limited resolution.
Funding
  • This work is funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 409792180 (Emmy Noether Programme, project: Real Virtual Humans) and Google Faculty Research Award
Reference
  • Marc Alexa, Johannes Behr, Daniel Cohen-Or, Shachar Fleishman, David Levin, and Claudio T Silva. Point set surfaces. In Proceedings Visualization, 200VIS’01., pages 21–29. IEEE, 2001. 5
    Google ScholarLocate open access versionFindings
  • Thiemo Alldieck, Marcus Magnor, Weipeng Xu, Christian Theobalt, and Gerard PonsMoll. Video based reconstruction of 3d people models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8387–8397, 2018. 3
    Google ScholarLocate open access versionFindings
  • Thiemo Alldieck, Gerard Pons-Moll, Christian Theobalt, and Marcus Magnor. Tex2shape: Detailed full human body geometry from a single image. In IEEE International Conference on Computer Vision (ICCV). IEEE, oct 2019. 3
    Google ScholarLocate open access versionFindings
  • Matan Atzmon and Yaron Lipman. Sal: Sign agnostic learning of shapes from raw data. arXiv preprint arXiv:1911.10414, 2019. 2, 3, 8, 9
    Findings
  • Andreas Bærentzen and Niels Jørgen Christensen. A technique for volumetric csg based on morphology. In Volume Graphics 2001, pages 117–130. Springer, 2001. 5
    Google ScholarLocate open access versionFindings
  • J Andreas Bærentzen. Manipulation of volumetric solids with applications to sculpting. Citeseer, 2002. 7
    Google ScholarLocate open access versionFindings
  • Dana Harry Ballard and Christopher M Brown. Computer vision. Prentice Hall, 1982. 3
    Google ScholarFindings
  • Fausto Bernardini, Joshua Mittleman, Holly Rushmeier, Cláudio Silva, and Gabriel Taubin. The ball-pivoting algorithm for surface reconstruction. IEEE transactions on visualization and computer graphics, 5(4):349–359, 1999. 5, 6
    Google ScholarLocate open access versionFindings
  • Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt, and Gerard PonsMoll. Combining implicit function learning and parametric models for 3d human reconstruction. In European Conference on Computer Vision (ECCV). Springer, August 2020. 2
    Google ScholarLocate open access versionFindings
  • Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt, and Gerard PonsMoll. Loopreg: Self-supervised learning of implicit surface correspondences, pose and shape for 3d human mesh registration. In Neural Information Processing Systems (NeurIPS)., December 2020. 2
    Google ScholarLocate open access versionFindings
  • Bharat Lal Bhatnagar, Garvita Tiwari, Christian Theobalt, and Gerard Pons-Moll. Multi-garment net: Learning to dress 3d people from images. In IEEE International Conference on Computer Vision (ICCV). IEEE, oct 2019. 3, 8
    Google ScholarLocate open access versionFindings
  • 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 repository. arXiv preprint arXiv:1512.03012, 2015. 1, 2, 7, 8
    Findings
  • Zhiqin Chen and Hao Zhang. Learning implicit fields for generative shape modeling. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pages 5939–5948, 2019. 2, 3
    Google ScholarLocate open access versionFindings
  • Julian Chibane, Thiemo Alldieck, and Gerard Pons-Moll. Implicit functions in feature space for 3d shape reconstruction and completion. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, jun 2020. 2, 3, 4, 5, 7, 8, 9
    Google ScholarLocate open access versionFindings
  • Julian Chibane and Gerard Pons-Moll. Implicit feature networks for texture completion from partial 3d data. In European Conference on Computer Vision (ECCV), Workshops. Springer, August 2020. 3
    Google ScholarLocate open access versionFindings
  • Christopher Bongsoo Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, and Silvio Savarese. 3d-r2n2: A unified approach for single and multi-view 3d object reconstruction. In Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII, pages 628–644, 203, 7
    Google ScholarLocate open access versionFindings
  • 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 1996, New Orleans, LA, USA, August 4-9, 1996, pages 303–312, 1996. 3
    Google ScholarLocate open access versionFindings
  • Angela Dai and Matthias Nießner. Scan2mesh: From unstructured range scans to 3d meshes. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pages 5574–5583, 2019. 3
    Google ScholarLocate open access versionFindings
  • Angela Dai, Charles Ruizhongtai Qi, and Matthias Nießner. Shape completion using 3d-encoder-predictor cnns and shape synthesis. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pages 6545–6554, 2017. 3
    Google ScholarLocate open access versionFindings
  • Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey Hinton, and Andrea Tagliasacchi. Cvxnets: Learnable convex decomposition. arXiv preprint arXiv:1909.05736, 2019. 3
    Findings
  • Boyang Deng, JP Lewis, Timothy Jeruzalski, Gerard Pons-Moll, Geoffrey Hinton, Mohammad Norouzi, and Andrea Tagliasacchi. Nasa neural articulated shape approximation. In The European Conference on Computer Vision (ECCV), August 2020. 3
    Google ScholarLocate open access versionFindings
  • Gabriella Sanniti di Baja. Well-shaped, stable, and reversible skeletons from the (3, 4)-distance transform. Journal of visual communication and image representation, 5(1):107–115, 1994. 3
    Google ScholarLocate open access versionFindings
  • Robert A Drebin, Loren Carpenter, and Pat Hanrahan. Volume rendering. ACM Siggraph Computer Graphics, 22(4):65–74, 1988. 2
    Google ScholarLocate open access versionFindings
  • Haoqiang Fan, Hao Su, and Leonidas J. Guibas. A point set generation network for 3d object reconstruction from a single image. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pages 2463–2471, 2017. 3, 7, 9
    Google ScholarLocate open access versionFindings
  • Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. IEEE transactions on pattern analysis and machine intelligence, 32(9):1627–1645, 2009. 3
    Google ScholarLocate open access versionFindings
  • Andrew W Fitzgibbon. Robust registration of 2d and 3d point sets. Image and vision computing, 21(13-14):1145–1153, 2003. 3
    Google ScholarLocate open access versionFindings
  • Kyle Genova, Forrester Cole, Avneesh Sud, Aaron Sarna, and Thomas Funkhouser. Deep structured implicit functions. In 2020 IEEE Conference on Computer Vision and Pattern Recognition, 2019. 2, 3
    Google ScholarLocate open access versionFindings
  • Georgia Gkioxari, Jitendra Malik, and Justin Johnson. Mesh R-CNN. CoRR, abs/1906.02739, 2019. 3
    Findings
  • Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, and Mathieu Aubry. A papier-mâché approach to learning 3d surface generation. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pages 216–224, 2018. 3
    Google ScholarLocate open access versionFindings
  • Erhan Gundogdu, Victor Constantin, Amrollah Seifoddini, Minh Dang, Mathieu Salzmann, and Pascal Fua. Garnet: A two-stream network for fast and accurate 3d cloth draping. In Proceedings of the IEEE International Conference on Computer Vision, pages 8739–8748, 2019. 3
    Google ScholarLocate open access versionFindings
  • Christian Hane, Shubham Tulsiani, and Jitendra Malik. Hierarchical surface prediction for 3d object reconstruction. In 2017 International Conference on 3D Vision, 3DV 2017, Qingdao, China, October 10-12, 2017, pages 412–420, 2017. 3
    Google ScholarLocate open access versionFindings
  • John C Hart. Sphere tracing: A geometric method for the antialiased ray tracing of implicit surfaces. The Visual Computer, 12(10):527–545, 1996. 6
    Google ScholarLocate open access versionFindings
  • Pedro Hermosilla, Tobias Ritschel, Pere-Pau Vázquez, Àlvar Vinacua, and Timo Ropinski. Monte carlo convolution for learning on non-uniformly sampled point clouds. ACM Transactions on Graphics (TOG), 37(6):1–12, 2018. 3
    Google ScholarLocate open access versionFindings
  • Eldar Insafutdinov and Alexey Dosovitskiy. Unsupervised learning of shape and pose with differentiable point clouds. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montréal, Canada., pages 2807–2817, 2018. 3
    Google ScholarLocate open access versionFindings
  • Mengqi Ji, Juergen Gall, Haitian Zheng, Yebin Liu, and Lu Fang. Surfacenet: An end-to-end 3d neural network for multiview stereopsis. In IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pages 2326–2334, 2017. 3
    Google ScholarLocate open access versionFindings
  • Chiyu Max Jiang, Avneesh Sud, Ameesh Makadia, Jingwei Huang, Matthias Nießner, and Thomas Funkhouser. Local implicit grid representations for 3d scenes. In 2020 IEEE Conference on Computer Vision and Pattern Recognition, 2020. 3
    Google ScholarLocate open access versionFindings
  • Mark W Jones, J Andreas Baerentzen, and Milos Sramek. 3d distance fields: A survey of techniques and applications. IEEE Transactions on visualization and Computer Graphics, 12(4):581–599, 2006. 3
    Google ScholarLocate open access versionFindings
  • Angjoo Kanazawa, Michael J. Black, David W. Jacobs, and Jitendra Malik. End-to-end recovery of human shape and pose. In IEEE Conf. on Computer Vision and Pattern Recognition. IEEE Computer Society, 2018. 3
    Google ScholarLocate open access versionFindings
  • Abhishek Kar, Christian Häne, and Jitendra Malik. Learning a multi-view stereo machine. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA, pages 365–376, 2017. 3
    Google ScholarLocate open access versionFindings
  • Nikos Kolotouros, Georgios Pavlakos, Michael J. Black, and Kostas Daniilidis. Learning to reconstruct 3d human pose and shape via model-fitting in the loop. CoRR, abs/1909.12828, 2019. 3
    Findings
  • Nikos Kolotouros, Georgios Pavlakos, and Kostas Daniilidis. Convolutional mesh regression for single-image human shape reconstruction. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pages 4501–4510, 2019. 3
    Google ScholarLocate open access versionFindings
  • Lubor Ladicky, Olivier Saurer, SoHyeon Jeong, Fabio Maninchedda, and Marc Pollefeys. From point clouds to mesh using regression. In IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pages 3913–3922, 2017. 3
    Google ScholarLocate open access versionFindings
  • Yann LeCun, Sumit Chopra, Raia Hadsell, M Ranzato, and F Huang. A tutorial on energy-based learning. Predicting structured data, 1(0), 2006. 4
    Google ScholarLocate open access versionFindings
  • Yiyi Liao, Simon Donné, and Andreas Geiger. Deep marching cubes: Learning explicit surface representations. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pages 2916–2925, 2018. 3
    Google ScholarLocate open access versionFindings
  • Yiyi Liao, Simon Donné, and Andreas Geiger. Deep marching cubes: Learning explicit surface representations. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pages 2916–2925, 2018. 7, 9
    Google ScholarLocate open access versionFindings
  • Zhijian Liu, Haotian Tang, Yujun Lin, and Song Han. Point-voxel cnn for efficient 3d deep learning. In Advances in Neural Information Processing Systems, pages 963–973, 2019. 3
    Google ScholarLocate open access versionFindings
  • Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, and Michael J Black. SMPL: A skinned multi-person linear model. ACM Transactions on Graphics, 34(6):248:1–248:16, 2015. 3
    Google ScholarLocate open access versionFindings
  • William E. Lorensen and Harvey E. Cline. Marching cubes: A high resolution 3d surface construction algorithm. In Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1987, Anaheim, California, USA, July 27-31, 1987, pages 163–169, 1987. 2
    Google ScholarLocate open access versionFindings
  • Lars M. Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, and Andreas Geiger. Occupancy networks: Learning 3d reconstruction in function space. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pages 4460–4470, 2019. 2, 3, 7, 9
    Google ScholarLocate open access versionFindings
  • Mateusz Michalkiewicz, Jhony K. Pontes, Dominic Jack, Mahsa Baktashmotlagh, and Anders P. Eriksson. Deep level sets: Implicit surface representations for 3d shape inference. CoRR, abs/1901.06802, 2019. 3
    Findings
  • Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis. arXiv preprint arXiv:2003.08934, 2020. 4
    Findings
  • Mohamed Omran, Christop Lassner, Gerard Pons-Moll, Peter Gehler, and Bernt Schiele. Neural body fitting: Unifying deep learning and model based human pose and shape estimation. In International Conf. on 3D Vision, 2018. 3
    Google ScholarLocate open access versionFindings
  • Jeong Joon Park, Peter Florence, Julian Straub, Richard A. Newcombe, and Steven Lovegrove. Deepsdf: Learning continuous signed distance functions for shape representation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pages 165–174, 2019. 2, 3, 5
    Google ScholarLocate open access versionFindings
  • Chaitanya Patel, Zhouyingcheng Liao, and Gerard Pons-Moll. Tailornet: Predicting clothing in 3d as a function of human pose, shape and garment style. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, jun 2020. 3
    Google ScholarLocate open access versionFindings
  • Mark Pauly, Richard Keiser, Leif P Kobbelt, and Markus Gross. Shape modeling with point-sampled geometry. ACM Transactions on Graphics (TOG), 22(3):641–650, 2003. 5
    Google ScholarLocate open access versionFindings
  • Ronald N Perry and Sarah F Frisken. Kizamu: A system for sculpting digital characters. In Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pages 47–56, 2001. 5
    Google ScholarLocate open access versionFindings
  • Gerard Pons-Moll, Sergi Pujades, Sonny Hu, and Michael Black. ClothCap: Seamless 4D clothing capture and retargeting. ACM Transactions on Graphics, 36(4), 2017. 3
    Google ScholarLocate open access versionFindings
  • Gerard Pons-Moll, Javier Romero, Naureen Mahmood, and Michael J. Black. Dyna: A model of dynamic human shape in motion. ACM Transactions on Graphics, (Proc. SIGGRAPH), 34(4):120:1–120:14, aug 2015. 3
    Google ScholarLocate open access versionFindings
  • Adrien Poulenard, Marie-Julie Rakotosaona, Yann Ponty, and Maks Ovsjanikov. Effective rotation-invariant point cnn with spherical harmonics kernels. In 2019 International Conference on 3D Vision (3DV), pages 47–56. IEEE, 2019. 3
    Google ScholarLocate open access versionFindings
  • Charles Ruizhongtai Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pages 77–85, 2017. 3, 5
    Google ScholarLocate open access versionFindings
  • Charles Ruizhongtai Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pages 77–85, 2017. 3
    Google ScholarLocate open access versionFindings
  • Can Qin, Haoxuan You, Lichen Wang, C-C Jay Kuo, and Yun Fu. Pointdan: A multiscale 3d domain adaption network for point cloud representation. In Advances in Neural Information Processing Systems, pages 7190–7201, 2019. 3
    Google ScholarLocate open access versionFindings
  • Anurag Ranjan, Timo Bolkart, Soubhik Sanyal, and Michael J. Black. Generating 3d faces using convolutional mesh autoencoders. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part III, pages 725–741, 2018. 3
    Google ScholarLocate open access versionFindings
  • http://virtualhumans.mpi-inf.mpg.de/ndf/.1
    Findings
  • Danilo Jimenez Rezende, S. M. Ali Eslami, Shakir Mohamed, Peter W. Battaglia, Max Jaderberg, and Nicolas Heess. Unsupervised learning of 3d structure from images. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, pages 4997–5005, 2016. 3
    Google ScholarLocate open access versionFindings
  • Gernot Riegler, Ali Osman Ulusoy, Horst Bischof, and Andreas Geiger. Octnetfusion: Learning depth fusion from data. In 2017 International Conference on 3D Vision, 3DV 2017, Qingdao, China, October 10-12, 2017, pages 57–66, 2017. 3
    Google ScholarLocate open access versionFindings
  • Shunsuke Saito, Zeng Huang, Ryota Natsume, Shigeo Morishima, Angjoo Kanazawa, and Hao Li. Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization. CoRR, abs/1905.05172, 2019. 3
    Findings
  • Dong Wook Shu, Sung Woo Park, and Junseok Kwon. 3d point cloud generative adversarial network based on tree structured graph convolutions. CoRR, abs/1905.06292, 2019. 3
    Findings
  • Vincent Sitzmann, Michael Zollhöfer, and Gordon Wetzstein. Scene representation networks: Continuous 3d-structure-aware neural scene representations. In Advances in Neural Information Processing Systems, pages 1119–1130, 2019. 2, 4
    Google ScholarLocate open access versionFindings
  • Cristian Sminchisescu and Alexandru Telea. Human pose estimation from silhouettes. a consistent approach using distance level sets. In Proceedings of the 10th international conference in central Europe on computer graphics, visualization and computer vision (WSCG 2002), 2002. 3
    Google ScholarLocate open access versionFindings
  • David Stutz and Andreas Geiger. Learning 3d shape completion from laser scan data with weak supervision. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pages 1955–1964, 2018. 3
    Google ScholarLocate open access versionFindings
  • Maxim Tatarchenko, Alexey Dosovitskiy, and Thomas Brox. Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs. In IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pages 2107–2115, 2017. 3
    Google ScholarLocate open access versionFindings
  • Hugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui, François Goulette, and Leonidas J. Guibas. Kpconv: Flexible and deformable convolution for point clouds. CoRR, abs/1904.08889, 2019. 3
    Findings
  • Garvita Tiwari, Bharat Lal Bhatnagar, Tony Tung, and Gerard Pons-Moll. Sizer: A dataset and model for parsing 3d clothing and learning size sensitive 3d clothing. In European Conference on Computer Vision (ECCV). Springer, August 2020. 3
    Google ScholarLocate open access versionFindings
  • Shubham Tulsiani, Tinghui Zhou, Alexei A. Efros, and Jitendra Malik. Multi-view supervision for single-view reconstruction via differentiable ray consistency. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pages 209–217, 2017. 3
    Google ScholarLocate open access versionFindings
  • Hsiao-Yu Tung, Hsiao-Wei Tung, Ersin Yumer, and Katerina Fragkiadaki. Self-supervised learning of motion capture. In Advances in Neural Information Processing Systems, pages 5236–5246, 2017. 3
    Google ScholarLocate open access versionFindings
  • Hao Wang, Nadav Schor, Ruizhen Hu, Haibin Huang, Daniel Cohen-Or, and Hui Huang. Global-to-local generative model for 3d shapes. ACM Trans. Graph., 37(6):214:1–214:10, 2018. 3
    Google ScholarLocate open access versionFindings
  • Nanyang Wang, Yinda Zhang, Zhuwen Li, Yanwei Fu, Wei Liu, and Yu-Gang Jiang. Pixel2mesh: Generating 3d mesh models from single RGB images. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XI, pages 55–71, 2018. 3
    Google ScholarLocate open access versionFindings
  • Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E Sarma, Michael M Bronstein, and Justin M Solomon. Dynamic graph cnn for learning on point clouds. Acm Transactions On Graphics (tog), 38(5):1–12, 2019. 3
    Google ScholarLocate open access versionFindings
  • Franz-Erich Wolter. Cut locus and medial axis in global shape interrogation and representation. MIT Design Laboratory Memorandum 92-2 and MIT Sea Grant Report, 1993. 5
    Google ScholarFindings
  • Jiajun Wu, Yifan Wang, Tianfan Xue, Xingyuan Sun, Bill Freeman, and Josh Tenenbaum. Marrnet: 3d shape reconstruction via 2.5d sketches. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA, pages 540–550, 2017. 3
    Google ScholarLocate open access versionFindings
  • Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum. Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, pages 82–90, 2016. 3
    Google ScholarLocate open access versionFindings
  • Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 3d shapenets: A deep representation for volumetric shapes. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015, pages 1912–1920, 2015. 3
    Google ScholarLocate open access versionFindings
  • Qiangeng Xu, Weiyue Wang, Duygu Ceylan, Radomír Mech, and Ulrich Neumann. DISN: deep implicit surface network for high-quality single-view 3d reconstruction. CoRR, abs/1905.10711, 2019. 7
    Findings
  • Guandao Yang, Xun Huang, Zekun Hao, Ming-Yu Liu, Serge J. Belongie, and Bharath Hariharan. Pointflow: 3d point cloud generation with continuous normalizing flows. CoRR, abs/1906.12320, 2019. 3
    Findings
  • Andrei Zanfir, Elisabeta Marinoiu, and Cristian Sminchisescu. Monocular 3d pose and shape estimation of multiple people in natural scenes–the importance of multiple scene constraints. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2148–2157, 2018. 3
    Google ScholarLocate open access versionFindings
  • Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Josh Tenenbaum, Bill Freeman, and Jiajun Wu. Learning to reconstruct shapes from unseen classes. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montréal, Canada., pages 2263–2274, 2018. 3
    Google ScholarLocate open access versionFindings
Author
Julian Chibane
Julian Chibane
Mohamad Aymen mir
Mohamad Aymen mir
Your rating :
0

 

Tags
Comments
小科