Skip to main content

Monocular 3D Object Reconstruction with GAN Inversion

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Abstract

Recovering a textured 3D mesh from a monocular image is highly challenging, particularly for in-the-wild objects that lack 3D ground truths. In this work, we present MeshInversion, a novel framework to improve the reconstruction by exploiting the generative prior of a 3D GAN pre-trained for 3D textured mesh synthesis. Reconstruction is achieved by searching for a latent space in the 3D GAN that best resembles the target mesh in accordance with the single view observation. Since the pre-trained GAN encapsulates rich 3D semantics in terms of mesh geometry and texture, searching within the GAN manifold thus naturally regularizes the realness and fidelity of the reconstruction. Importantly, such regularization is directly applied in the 3D space, providing crucial guidance of mesh parts that are unobserved in the 2D space. Experiments on standard benchmarks show that our framework obtains faithful 3D reconstructions with consistent geometry and texture across both observed and unobserved parts. Moreover, it generalizes well to meshes that are less commonly seen, such as the extended articulation of deformable objects. Code is released at https://github.com/junzhezhang/mesh-inversion.

Bo Dai completed this work when he was with S-Lab, NTU.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds. In: ICML (2018)

    Google Scholar 

  2. Bau, D., et al.: Semantic photo manipulation with a generative image prior. In: SIGGRAPH (2019)

    Google Scholar 

  3. Bau, D., et al.: Seeing what a GAN cannot generate. In: ICCV (2019)

    Google Scholar 

  4. Bhattad, A., Dundar, A., Liu, G., Tao, A., Catanzaro, B.: View generalization for single image textured 3D models. In: CVPR (2021)

    Google Scholar 

  5. Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2019)

    Google Scholar 

  6. Chen, W., et al.: Learning to predict 3D objects with an interpolation-based differentiable renderer. In: NeurIPS (2019)

    Google Scholar 

  7. Ye, Y., et al.: Shelf-supervised mesh prediction in the wild. In: CVPR (2021)

    Google Scholar 

  8. Gecer, B., Ploumpis, S., Kotsia, I., Zafeiriou, S.: GANFIT: generative adversarial network fitting for high fidelity 3D face reconstruction. In: CVPR (2019)

    Google Scholar 

  9. Girdhar, R., Fouhey, D.F., Rodriguez, M., Gupta, A.: Learning a predictable and generative vector representation for objects. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 484–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_29

    Chapter  Google Scholar 

  10. Goel, S., Kanazawa, A., Malik, J.: Shape and viewpoint without keypoints. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 88–104. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_6

    Chapter  Google Scholar 

  11. Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)

    Google Scholar 

  12. Gu, J., Shen, Y., Zhou, B.: Image processing using multi-code GAN prior. In: CVPR (2020)

    Google Scholar 

  13. Henderson, P., Tsiminaki, V., Lampert, C.H.: Leveraging 2D data to learn textured 3D mesh generation. In: CVPR (2020)

    Google Scholar 

  14. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local NASH equilibrium. In: NeurIPS (2017)

    Google Scholar 

  15. Hu, T., Wang, L., Xu, X., Liu, S., Jia, J.: Self-supervised 3D mesh reconstruction from single images. In: CVPR (2021)

    Google Scholar 

  16. Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)

    Google Scholar 

  17. Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_43

    Chapter  Google Scholar 

  18. Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: CVPR (2018)

    Google Scholar 

  19. Kanazawa, A., Tulsiani, S., Efros, A.A., Malik, J.: Learning category-specific mesh reconstruction from image collections. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 386–402. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01267-0_23

    Chapter  Google Scholar 

  20. Kar, A., Tulsiani, S., Carreira, J., Malik, J.: Category-specific object reconstruction from a single image. In: CVPR (2015)

    Google Scholar 

  21. Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)

    Google Scholar 

  22. Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: ICLR (2014)

    Google Scholar 

  23. Kirillov, A., Wu, Y., He, K., Girshick, R.: PointRend: image segmentation as rendering. In: CVPR (2020)

    Google Scholar 

  24. Li, X., et al.: Self-supervised single-view 3D reconstruction via semantic consistency. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 677–693. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_40

    Chapter  Google Scholar 

  25. Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV (2017)

    Google Scholar 

  26. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  27. Lipton, Z.C., Tripathi, S.: Precise recovery of latent vectors from generative adversarial networks. CoRR arXiv:1702.04782 (2017)

  28. Liu, S., Chen, W., Li, T., Li, H.: Soft rasterizer: differentiable rendering for unsupervised single-view mesh reconstruction. In: ICCV (2019)

    Google Scholar 

  29. Ma, F., Ayaz, U., Karaman, S.: Invertibility of convolutional generative networks from partial measurements. In: NeurIPS (2018)

    Google Scholar 

  30. Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Paul Smolley, S.: Least squares generative adversarial networks. In: ICCV (2017)

    Google Scholar 

  31. Mechrez, R., Talmi, I., Zelnik-Manor, L.: The contextual loss for image transformation with non-aligned data. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 800–815. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_47

    Chapter  Google Scholar 

  32. Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: CVPR (2019)

    Google Scholar 

  33. Niemeyer, M., Mescheder, L., Oechsle, M., Geiger, A.: Differentiable volumetric rendering: learning implicit 3D representations without 3D supervision. In: CVPR (2020)

    Google Scholar 

  34. Oechsle, M., Peng, S., Geiger, A.: UNISURF: unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In: ICCV (2021)

    Google Scholar 

  35. Pan, J., Han, X., Chen, W., Tang, J., Jia, K.: Deep mesh reconstruction from single RGB images via topology modification networks. In: ICCV (2019)

    Google Scholar 

  36. Pan, X., Dai, B., Liu, Z., Loy, C.C., Luo, P.: Do 2D GANs know 3D shape? Unsupervised 3D shape reconstruction from 2D image GANs. In: ICLR (2021)

    Google Scholar 

  37. Pan, X., Zhan, X., Dai, B., Lin, D., Loy, C.C., Luo, P.: Exploiting deep generative prior for versatile image restoration and manipulation. PAMI (2021)

    Google Scholar 

  38. Pavllo, D., Spinks, G., Hofmann, T., Moens, M.F., Lucchi, A.: Convolutional generation of textured 3D meshes. In: NeurIPS (2020)

    Google Scholar 

  39. Rematas, K., Martin-Brualla, R., Ferrari, V.: ShaRF: shape-conditioned radiance fields from a single view. In: ICML (2021)

    Google Scholar 

  40. Sanyal, S., Bolkart, T., Feng, H., Black, M.J.: Learning to regress 3D face shape and expression from an image without 3D supervision. In: CVPR (2019)

    Google Scholar 

  41. Shu, D.W., Park, S.W., Kwon, J.: 3D point cloud generative adversarial network based on tree structured graph convolutions. In: ICCV (2019)

    Google Scholar 

  42. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)

    Google Scholar 

  43. Smith, E.J., Meger, D.: Improved adversarial systems for 3D object generation and reconstruction. In: CoRL (2017)

    Google Scholar 

  44. Tulsiani, S., Zhou, T., Efros, A.A., Malik, J.: Multi-view supervision for single-view reconstruction via differentiable ray consistency. In: CVPR (2017)

    Google Scholar 

  45. Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD birds-200-2011 dataset (2011)

    Google Scholar 

  46. Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W., Jiang, Y.-G.: Pixel2Mesh: generating 3D mesh models from single RGB images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 55–71. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_4

    Chapter  Google Scholar 

  47. Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction. In: NeurIPS (2021)

    Google Scholar 

  48. Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: NeurIPS (2016)

    Google Scholar 

  49. Xiang, Y., Mottaghi, R., Savarese, S.: Beyond PASCAL: a benchmark for 3D object detection in the wild. In: WACV (2014)

    Google Scholar 

  50. Xie, J., Zheng, Z., Gao, R., Wang, W., Zhu, S.C., Wu, Y.N.: Learning descriptor networks for 3D shape synthesis and analysis. In: CVPR (2018)

    Google Scholar 

  51. Yariv, L., et al.: Multiview neural surface reconstruction by disentangling geometry and appearance. In: NeurIPS (2020)

    Google Scholar 

  52. Zhang, J., et al.: Unsupervised 3D shape completion through GAN inversion. In: CVPR (2021)

    Google Scholar 

  53. Zhu, J., Shen, Y., Zhao, D., Zhou, B.: In-domain GAN inversion for real image editing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 592–608. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58520-4_35

    Chapter  Google Scholar 

  54. Zhu, J.Y., et al.: Visual object networks: image generation with disentangled 3D representations. In: NeurIPS (2018)

    Google Scholar 

Download references

Acknowledgement

This study is supported under the RIE2020 Industry Alignment Fund – Industry Collaboration Projects (IAF-ICP) Funding Initiative, Singapore MOE AcRF Tier 2 (MOE-T2EP20221-0011), Shanghai AI Laboratory, as well as cash and in-kind contribution from the industry partners.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Chen Change Loy .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 2937 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhang, J., Ren, D., Cai, Z., Yeo, C.K., Dai, B., Loy, C.C. (2022). Monocular 3D Object Reconstruction with GAN Inversion. 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 13661. Springer, Cham. https://doi.org/10.1007/978-3-031-19769-7_39

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19769-7_39

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19768-0

  • Online ISBN: 978-3-031-19769-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics