Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15124))

Included in the following conference series:

  • 74 Accesses

Abstract

We introduce a novel framework for 3D human avatar generation and personalization, leveraging text prompts to enhance user engagement and customization. Central to our approach are key innovations aimed at overcoming the challenges in photo-realistic avatar synthesis. Firstly, we utilize a conditional Neural Radiance Fields (NeRF) model, trained on a large-scale unannotated multi-view dataset, to create a versatile initial solution space that accelerates and diversifies avatar generation. Secondly, we develop a geometric prior, leveraging the capabilities of Text-to-Image Diffusion Models, to ensure superior view invariance and enable direct optimization of avatar geometry. These foundational ideas are complemented by our optimization pipeline built on Variational Score Distillation (VSD), which mitigates texture loss and over-saturation issues. As supported by our extensive experiments, these strategies collectively enable the creation of custom avatars with unparalleled visual quality and better adherence to input text prompts. You can find more results and videos in our website: syntec-research.github.io/MagicMirror.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /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 64.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
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. Athar, S., Xu, Z., Sunkavalli, K., Shechtman, E., Shu, Z.: RigNeRF: fully controllable neural 3D portraits. In: CVPR 2022, pp. 20332–20341 (2022)

    Google Scholar 

  2. Bai, Z., Cui, Z., Liu, X., Tan, P.: Riggable 3D face reconstruction via in-network optimization. In: CVPR 2021, pp. 6216–6225 (2021)

    Google Scholar 

  3. Bai, Z., et al.: Learning personalized high quality volumetric head avatars from monocular RGB videos. In: CVPR 2023, pp. 16890–16900 (2023)

    Google Scholar 

  4. Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-Nerf 360: unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470–5479 (2022)

    Google Scholar 

  5. Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In: SIGGRAPH 1999, pp. 187–194 (1999)

    Google Scholar 

  6. Bojanowski, P., Joulin, A., Lopez-Paz, D., Szlam, A.: Optimizing the latent space of generative networks. In: Proceedings of the 35th International Conference on Machine Learning, pp. 2640–3498 (2018)

    Google Scholar 

  7. Bühler, M.C., et al.: Preface: a data-driven volumetric prior for few-shot ultra high-resolution face synthesis. In: ICCV 2023, pp. 3379–3390 (2023)

    Google Scholar 

  8. Cao, C., et al.: Authentic volumetric avatars from a phone scan. ACM Trans. Graph. 41(4), 163:1–163:19 (2022)

    Google Scholar 

  9. Cao, C., Wu, H., Weng, Y., Shao, T., Zhou, K.: Real-time facial animation with image-based dynamic avatars. ACM Trans. Graph. 35(4), 126:1–126:12 (2016)

    Google Scholar 

  10. Cao, Y., Cao, Y., Han, K., Shan, Y., Wong, K.K.: Dreamavatar: text-and-shape guided 3D human avatar generation via diffusion models. CoRR abs/2304.00916 (2023)

    Google Scholar 

  11. Chan, E.R., et al.: Efficient geometry-aware 3d generative adversarial networks. In: CVPR 2022, pp. 16102–16112 (2022)

    Google Scholar 

  12. Chan, E.R., et al.: Generative novel view synthesis with 3D-aware diffusion models. In: ICCV 2023, pp. 4194–4206 (2023)

    Google Scholar 

  13. Chaudhuri, B., Vesdapunt, N., Shapiro, L., Wang, B.: Personalized face modeling for improved face reconstruction and motion retargeting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 142–160. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_9

    Chapter  Google Scholar 

  14. Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3D: disentangling geometry and appearance for high-quality text-to-3D content creation. In: ICCV 2023, pp. 22189–22199 (2023)

    Google Scholar 

  15. Chen, S., Liu, F., Lai, Y., Rosin, P.L., Li, C., Fu, H., Gao, L.: Deepfaceediting: deep face generation and editing with disentangled geometry and appearance control. ACM Trans. Graph. 40(4), 90:1–90:15 (2021)

    Google Scholar 

  16. Daněček, R., Black, M.J., Bolkart, T.: EMOCA: emotion driven monocular face capture and animation. In: CVPR (2022)

    Google Scholar 

  17. Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: CVPR (2023)

    Google Scholar 

  18. Du, Y., Li, S., Mordatch, I.: Compositional visual generation with energy based models. In: Neural Information Processing Systems (2020). https://api.semanticscholar.org/CorpusID:214223619

  19. Gafni, G., Thies, J., Zollhöfer, M., Nießner, M.: Dynamic neural radiance fields for monocular 4D facial avatar reconstruction. In: CVPR 2021, pp. 8649–8658 (2021)

    Google Scholar 

  20. Gal, R., Patashnik, O., Maron, H., Bermano, A.H., Chechik, G., Cohen-Or, D.: StyleGAN-nada: clip-guided domain adaptation of image generators. ACM Trans. Graph. 41(4), 141:1–141:13 (2022)

    Google Scholar 

  21. Garrido, P., et al.: Reconstruction of personalized 3D face rigs from monocular video. ACM Trans. Graph. 35(3), 28:1–28:15 (2016)

    Google Scholar 

  22. Han, X., et al.: HeadSculpt: crafting 3D head avatars with text. In: NeurIPS 2023 (2023)

    Google Scholar 

  23. Haque, A., Tancik, M., Efros, A.A., Holynski, A., Kanazawa, A.: Instruct-NeRF2NeRF: editing 3D scenes with instructions. In: CVPR (2023)

    Google Scholar 

  24. Ho, J., Jain, A., Abbeel, P.: Denoising Diffusion Probabilistic Models (2020)

    Google Scholar 

  25. Ho, J., Salimans, T.: Classifier-free diffusion guidance. CoRR abs/2207.12598 (2022)

    Google Scholar 

  26. Hong, F., Zhang, M., Pan, L., Cai, Z., Yang, L., Liu, Z.: Avatarclip: zero-shot text-driven generation and animation of 3D avatars. ACM Trans. Graph. 41(4), 161:1–161:19 (2022)

    Google Scholar 

  27. Hu, E.J., et al.: Lora: low-rank adaptation of large language models. In: ICLR 2022 (2022)

    Google Scholar 

  28. Hu, L., et al.: Avatar digitization from a single image for real-time rendering. ACM Trans. Graph. 36(6), 195:1–195:14 (2017)

    Google Scholar 

  29. Huang, X., Shao, R., Zhang, Q., Zhang, H., Feng, Y., Liu, Y., Wang, Q.: HumanNorm: learning normal diffusion model for high-quality and realistic 3d human generation. CoRR abs/2310.01406 (2023)

    Google Scholar 

  30. Huang, Y., Wang, J., Shi, Y., Qi, X., Zha, Z., Zhang, L.: Dreamtime: an improved optimization strategy for text-to-3D content creation. CoRR abs/2306.12422 (2023)

    Google Scholar 

  31. Huang, Y., et al.: Dreamwaltz: make a scene with complex 3d animatable avatars. In: NeurIPS 2023 (2023)

    Google Scholar 

  32. Ichim, A.E., Bouaziz, S., Pauly, M.: Dynamic 3D avatar creation from hand-held video input. ACM Trans. Graph. 34(4), 45:1–45:14 (2015)

    Google Scholar 

  33. Jiang, R., et al.: Avatarcraft: transforming text into neural human avatars with parameterized shape and pose control. In: ICCV 2023, pp. 14325–14336 (2023)

    Google Scholar 

  34. Jun, H., Nichol, A.: Shap-e: generating conditional 3D implicit functions. CoRR abs/2305.02463 (2023)

    Google Scholar 

  35. Karnewar, A., Vedaldi, A., Novotný, D., Mitra, N.J.: HOLODIFFUSION: training a 3D diffusion model using 2D images. In: CVPR 2023, pp. 18423–18433 (2023)

    Google Scholar 

  36. Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 43(12), 4217–4228 (2021)

    Article  Google Scholar 

  37. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: CVPR 2020, pp. 8107–8116 (2020)

    Google Scholar 

  38. Kerbl, B., Kopanas, G., Leimkühler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139:1–139:14 (2023)

    Google Scholar 

  39. Kim, H., et al.: Deep video portraits. ACM Trans. Graph. 37(4), 163 (2018)

    Article  Google Scholar 

  40. Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation. ArXiv abs/2305.01569 (2023). https://api.semanticscholar.org/CorpusID:258437096

  41. Kolotouros, N., Alldieck, T., Zanfir, A., Bazavan, E.G., Fieraru, M., Sminchisescu, C.: Dreamhuman: animatable 3D avatars from text. In: NeurIPS 2023 (2023)

    Google Scholar 

  42. Lin, C., et al.: Magic3D: high-resolution text-to-3D content creation. In: CVPR 2023, pp. 300–309 (2023)

    Google Scholar 

  43. Liu, N., Li, S., Du, Y., Tenenbaum, J.B., Torralba, A.: Learning to compose visual relations. ArXiv abs/2111.09297 (2021). https://api.semanticscholar.org/CorpusID:244270027

  44. Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. ArXiv abs/2206.01714 (2022). https://api.semanticscholar.org/CorpusID:249375227

  45. Liu, R., Wu, R., Hoorick, B.V., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: Zero-shot one image to 3d object. In: ICCV 2023, pp. 9264–9275 (2023)

    Google Scholar 

  46. Liu, Y., et al.: Syncdreamer: generating multiview-consistent images from a single-view image. CoRR abs/2309.03453 (2023)

    Google Scholar 

  47. Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. 34(6), 248:1–248:16 (2015)

    Google Scholar 

  48. Luo, S., Hu, W.: Diffusion probabilistic models for 3D point cloud generation. In: CVPR 2021, pp. 2837–2845 (2021)

    Google Scholar 

  49. Mendiratta, M., et al.: Avatarstudio: text-driven editing of 3D dynamic human head avatars. ACM Trans. Graph. 42(6), 226:1–226:18 (2023)

    Google Scholar 

  50. Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: Representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405–421. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_24

    Chapter  Google Scholar 

  51. Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-e: a system for generating 3D point clouds from complex prompts. CoRR abs/2212.08751 (2022)

    Google Scholar 

  52. Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. In: ICLR 2023 (2023)

    Google Scholar 

  53. Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML 2021, vol. 139, pp. 8748–8763 (2021)

    Google Scholar 

  54. Raj, A., et al.: DreamBooth3D: subject-driven text-to-3D generation (2023)

    Google Scholar 

  55. Raj, A., et al.: Pixel-aligned volumetric avatars. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11733–11742 (2021)

    Google Scholar 

  56. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR 2022, pp. 10674–10685 (2022)

    Google Scholar 

  57. Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR 2023, pp. 22500–22510 (2023)

    Google Scholar 

  58. Shen, T., Gao, J., Yin, K., Liu, M., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. In: NeurIPS 2021, pp. 6087–6101 (2021)

    Google Scholar 

  59. Shen, Y., Yang, C., Tang, X., Zhou, B.: InterFaceGAN: interpreting the disentangled face representation learned by GANs. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 2004–2018 (2022)

    Article  Google Scholar 

  60. Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. CoRR abs/2308.16512 (2023)

    Google Scholar 

  61. Shue, J.R., Chan, E.R., Po, R., Ankner, Z., Wu, J., Wetzstein, G.: 3D neural field generation using triplane diffusion. In: CVPR 2023, pp. 20875–20886 (2023)

    Google Scholar 

  62. Tang, J., et al.: Make-it-3D: high-fidelity 3D creation from a single image with diffusion prior. In: ICCV 2023, pp. 22762–22772 (2023)

    Google Scholar 

  63. Tewari, A., et al.: FML: face model learning from videos. In: CVPR 2019, pp. 10812–10822 (2019)

    Google Scholar 

  64. Thies, J., Zollhöfer, M., Stamminger, M., Theobalt, C., Nießner, M.: Face2face: Real-time face capture and reenactment of RGB videos. In: CVPR 2016, pp. 2387–2395 (2016)

    Google Scholar 

  65. Trevithick, A., et al.: Real-time radiance fields for single-image portrait view synthesis. ACM Trans. Graph. 42(4), 135:1–135:15 (2023)

    Google Scholar 

  66. Tsalicoglou, C., Manhardt, F., Tonioni, A., Niemeyer, M., Tombari, F.: TextMesh: generation of realistic 3d meshes from text prompts. CoRR abs/2304.12439 (2023)

    Google Scholar 

  67. Wang, C., Jiang, R., Chai, M., He, M., Chen, D., Liao, J.: NeRF-Art: text-driven neural radiance fields stylization. IEEE TVCG (2023)

    Google Scholar 

  68. Wang, C., Jiang, R., Chai, M., He, M., Chen, D., Liao, J.: Nerf-art: text-driven neural radiance fields stylization. IEEE Trans. Vis. Comput. Graph. 01, 1–15 (2023)

    Google Scholar 

  69. Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score Jacobian chaining: lifting pretrained 2D diffusion models for 3D generation. In: CVPR 2023, pp. 12619–12629 (2023)

    Google Scholar 

  70. Wang, T., et al.: RODIN: a generative model for sculpting 3D digital avatars using diffusion. In: CVPR 2023, pp. 4563–4573 (2023)

    Google Scholar 

  71. Wang, Z., et al.: ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: NeurIPS 2023 (2023)

    Google Scholar 

  72. Watson, D., Chan, W., Martin-Brualla, R., Ho, J., Tagliasacchi, A., Norouzi, M.: Novel view synthesis with diffusion models. In: ICLR 2023 (2023)

    Google Scholar 

  73. Weise, T., Bouaziz, S., Li, H., Pauly, M.: Realtime performance-based facial animation. ACM Trans. Graph. 30(4), 77 (2011)

    Article  Google Scholar 

  74. Xu, Y., Yang, Z., Yang, Y.: SEEAvatar: photorealistic text-to-3D avatar generation with constrained geometry and appearance. CoRR abs/2312.08889 (2023)

    Google Scholar 

  75. Zeng, Y., Lu, Y., Ji, X., Yao, Y., Zhu, H., Cao, X.: Avatarbooth: high-quality and customizable 3d human avatar generation. CoRR abs/2306.09864 (2023)

    Google Scholar 

  76. Zhang, L., et al.: DreamFace: progressive generation of animatable 3D faces under text guidance. ACM Trans. Graph. 42(4), 138:1–138:16 (2023)

    Google Scholar 

  77. Zheng, Y., Abrevaya, V.F., Bühler, M.C., Chen, X., Black, M.J., Hilliges, O.: I M avatar: implicit morphable head avatars from videos. In: CVPR 2022, pp. 13535–13545 (2022)

    Google Scholar 

  78. Zhou, Z., Tulsiani, S.: SparseFusion: distilling view-conditioned diffusion for 3D reconstruction. In: CVPR 2023, pp. 12588–12597 (2023)

    Google Scholar 

  79. Zhu, P., Abdal, R., Femiani, J., Wonka, P.: Mind the gap: domain gap control for single shot domain adaptation for generative adversarial networks. In: ICLR 2022 (2022)

    Google Scholar 

Download references

Acknowledgements

We would like to thank Prof. Octavia Camps and ONR grant N00014-21-1-2431 from NCI for their support.

Author information

Authors and Affiliations

  1. Google AR, Mountain View, USA

    Armand Comas-Massagué, Di Qiu, Menglei Chai, Marcel Bühler, Amit Raj, Qiangeng Xu, Mark Matthews, Paulo Gotardo, Sergio Orts-Escolano & Thabo Beeler

  2. Northeastern University, Boston, USA

    Armand Comas-Massagué

  3. ETH Zürich, Zürich, Switzerland

    Marcel Bühler

  4. Google DeepMind, London, UK

    Ruiqi Gao

Authors
  1. Armand Comas-Massagué
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Di Qiu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Menglei Chai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Marcel Bühler
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Amit Raj
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ruiqi Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Qiangeng Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Mark Matthews
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Paulo Gotardo
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Sergio Orts-Escolano
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Thabo Beeler
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Di Qiu .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Germany

    Stefan Roth

  4. Princeton University, Princeton, NJ, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 7001 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 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

Comas-Massagué, A. et al. (2025). MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15124. Springer, Cham. https://doi.org/10.1007/978-3-031-72848-8_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72848-8_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72847-1

  • Online ISBN: 978-3-031-72848-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation