Skip to main content

2020 | OriginalPaper | Buchkapitel

Single View 3D Reconstruction with Category Information Learning

verfasst von : Weihong Cao, Fei Hu, Long Ye, Qin Zhang

Erschienen in: Digital TV and Wireless Multimedia Communication

Verlag: Springer Singapore

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

3D reconstruction from single image is a classical problem in computer vision. Due to the fact that the information contained in one single image is not sufficient for 3D shape reconstruction, the existing model cannot reconstruct 3D models very well. To tackle this problem, we propose a novel model which effectively utilizes the category information of objects to improve the performance of network on single view 3D reconstruction. Our model consists of two parts: rough shape generation network (RSGN) and category comparison network (CCN). RSGN can learn the characteristics of objects in the same category through the comparison part CCN. In the experiments, we verify the feasibility of our model on the ShapeNet dataset, and the results confirm our framework.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. Comput. Sci. (2015) Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. Comput. Sci. (2015)
2.
Zurück zum Zitat Xiang, Y., Roozbeh, M., Savarese, S.: Beyond PASCAL: a benchmark for 3D object detection in the wild. In: Workshop on Applications of Computer Vision, pp. 75–82 (2014) Xiang, Y., Roozbeh, M., Savarese, S.: Beyond PASCAL: a benchmark for 3D object detection in the wild. In: Workshop on Applications of Computer Vision, pp. 75–82 (2014)
4.
Zurück zum Zitat Lim, J.J., Pirsiavash, H., Torralba, A.: Parsing IKEA objects: fine pose estimation. In: 2013 IEEE International Conference on Computer Vision (ICCV). IEEE Computer Society (2013) Lim, J.J., Pirsiavash, H., Torralba, A.: Parsing IKEA objects: fine pose estimation. In: 2013 IEEE International Conference on Computer Vision (ICCV). IEEE Computer Society (2013)
5.
Zurück zum Zitat Sun, X., et al.: Pix3D: dataset and methods for single-image 3D shape modeling. In: Computer Vision and Pattern Recognition, pp. 2974–2983 (2018) Sun, X., et al.: Pix3D: dataset and methods for single-image 3D shape modeling. In: Computer Vision and Pattern Recognition, pp. 2974–2983 (2018)
6.
Zurück zum Zitat Wu, N.Z., et al.: 3D ShapeNets: a deep representation for volumetric shape modeling. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society (2015) Wu, N.Z., et al.: 3D ShapeNets: a deep representation for volumetric shape modeling. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society (2015)
7.
Zurück zum Zitat Lee, H., et al.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: International Conference on Machine Learning, pp. 609–616 (2009) Lee, H., et al.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: International Conference on Machine Learning, pp. 609–616 (2009)
10.
Zurück zum Zitat Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRef Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRef
11.
Zurück zum Zitat Yan, X., et al.: Perspective transformer nets: learning single-view 3D object reconstruction without 3D supervision. In: Neural Information Processing Systems, pp. 1696–1704 (2016) Yan, X., et al.: Perspective transformer nets: learning single-view 3D object reconstruction without 3D supervision. In: Neural Information Processing Systems, pp. 1696–1704 (2016)
14.
Zurück zum Zitat Novotny, D., Larlus, D., Vedaldi, A.: Learning 3D object categories by looking around them. In: International Conference on Computer Vision, pp. 5228–5237 (2017) Novotny, D., Larlus, D., Vedaldi, A.: Learning 3D object categories by looking around them. In: International Conference on Computer Vision, pp. 5228–5237 (2017)
15.
Zurück zum Zitat Zhu, R., et al.: Rethinking reprojection: closing the loop for pose-aware shape reconstruction from a single image. In: International Conference on Computer Vision, pp. 57–65 (2017) Zhu, R., et al.: Rethinking reprojection: closing the loop for pose-aware shape reconstruction from a single image. In: International Conference on Computer Vision, pp. 57–65 (2017)
16.
Zurück zum Zitat Rezende, D.J., et al.: Unsupervised learning of 3D structure from images. arXiv: Computer Vision and Pattern Recognition (2016) Rezende, D.J., et al.: Unsupervised learning of 3D structure from images. arXiv: Computer Vision and Pattern Recognition (2016)
17.
Zurück zum Zitat Hane, C., Tulsiani, S., Malik, J.: Hierarchical surface prediction for 3D object reconstruction. In: International Conference on 3D Vision, pp. 412–420 (2017) Hane, C., Tulsiani, S., Malik, J.: Hierarchical surface prediction for 3D object reconstruction. In: International Conference on 3D Vision, pp. 412–420 (2017)
19.
Zurück zum Zitat Tulsiani, S., et al.: Multi-view supervision for single-view reconstruction via differentiable ray consistency. arXiv: Computer Vision and Pattern Recognition (2017) Tulsiani, S., et al.: Multi-view supervision for single-view reconstruction via differentiable ray consistency. arXiv: Computer Vision and Pattern Recognition (2017)
20.
Zurück zum Zitat Wu, J., et al.: MarrNet: 3D shape reconstruction via 2.5D sketches. In: Neural Information Processing Systems, pp. 540–550 (2017) Wu, J., et al.: MarrNet: 3D shape reconstruction via 2.5D sketches. In: Neural Information Processing Systems, pp. 540–550 (2017)
21.
Zurück zum Zitat Fan, H., Su, H., Guibas, L.J.: A point set generation network for 3D object reconstruction from a single image. In: Computer Vision and Pattern Recognition, pp. 2463–2471 (2017) Fan, H., Su, H., Guibas, L.J.: A point set generation network for 3D object reconstruction from a single image. In: Computer Vision and Pattern Recognition, pp. 2463–2471 (2017)
22.
Zurück zum Zitat Goodfellow, I.J., et al.: Generative adversarial nets. In: Neural Information Processing Systems, pp. 2672–2680 (2014) Goodfellow, I.J., et al.: Generative adversarial nets. In: Neural Information Processing Systems, pp. 2672–2680 (2014)
23.
Zurück zum Zitat Wu, J., et al.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: Computer Vision and Pattern Recognition (2016) Wu, J., et al.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: Computer Vision and Pattern Recognition (2016)
24.
Zurück zum Zitat Gadelha, M., Maji, S., Wang, R.: 3D shape induction from 2D views of multiple objects. In: International Conference on 3D Vision, pp. 402–411 (2017) Gadelha, M., Maji, S., Wang, R.: 3D shape induction from 2D views of multiple objects. In: International Conference on 3D Vision, pp. 402–411 (2017)
25.
Zurück zum Zitat Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. NIPS Curran Associates Inc. (2012) Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. NIPS Curran Associates Inc. (2012)
26.
Zurück zum Zitat Tatarchenko, M., et al.: What do single-view 3D reconstruction networks learn? In: Computer Vision and Pattern Recognition (2019) Tatarchenko, M., et al.: What do single-view 3D reconstruction networks learn? In: Computer Vision and Pattern Recognition (2019)
28.
Zurück zum Zitat Groueix, T., et al.: AtlasNet: a Papier-Mâché approach to learning 3D surface generation. In: Computer Vision and Pattern Recognition (2018) Groueix, T., et al.: AtlasNet: a Papier-Mâché approach to learning 3D surface generation. In: Computer Vision and Pattern Recognition (2018)
29.
Zurück zum Zitat Zhao, Y., et al.: 3D point-capsule networks. In: Computer Vision and Pattern Recognition, pp. 1009–1018 (2018) Zhao, Y., et al.: 3D point-capsule networks. In: Computer Vision and Pattern Recognition, pp. 1009–1018 (2018)
30.
Zurück zum Zitat Hu, F., et al.: 3D VAE-attention network: a parallel system for single-view 3D reconstruction. In: Pacific Graphics (2018) Hu, F., et al.: 3D VAE-attention network: a parallel system for single-view 3D reconstruction. In: Pacific Graphics (2018)
Metadaten
Titel
Single View 3D Reconstruction with Category Information Learning
verfasst von
Weihong Cao
Fei Hu
Long Ye
Qin Zhang
Copyright-Jahr
2020
Verlag
Springer Singapore
DOI
https://doi.org/10.1007/978-981-15-3341-9_33

Neuer Inhalt