Nothing Special   »   [go: up one dir, main page]

Skip to main content

X-NR: Towards An Extended Reality-Driven Human Evaluation Framework for Neural-Rendering

  • Conference paper
  • First Online:
Extended Reality (XR Salento 2024)

Abstract

The joint usage of Extended Reality (XR) and Artificial Intelligence (AI) has enabled different Metaverse-related use cases. Such paradigms were recently adopted for immersive content creation, particularly considering Neural Rendering (NR) techniques to project scenes from the real world in the 3D realm. These methods are particularly beneficial in the field of Cultural Heritage (CH), where digitizing and visualizing cultural assets in 3D is crucial. However, current evaluation protocols lack a robust integration of human judgments through a Human-In-The-Loop (HITL) approach to humanly evaluate the quality of the generated 3D models, which could also support model optimization. To bridge this gap, we here introduce X-NR, a novel XR framework designed to evaluate and compare 3D reconstruction methodologies, including NR in the context of CH. We contextualize and validate such a framework through case studies on cultural heritage sites in the Marche region (Italy), employing various data-capturing and 3D reconstruction methodologies. The study concludes with a validation of the framework by CH domain experts, underscoring its potential advantages over traditional 3D editing software.

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

Access this chapter

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

Notes

  1. 1.

    https://www.dji-store.it/categoria/droni-con-fotocamera/dji-mavic/.

  2. 2.

    https://www.faro.com/it-IT/Products/Hardware/Focus-Laser-Scanners.

  3. 3.

    Meta XR SDK documentation.

References

  1. Achiam, J., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)

  2. Balloni, E., Gorgoglione, L., Paolanti, M., Mancini, A., Pierdicca, R.: Few shot photogrametry: a comparison between nerf and mvs-sfm for the documentation of cultural heritage. Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci. 48, 155–162 (2023)

    Article  Google Scholar 

  3. Brooke, J., et al.: Sus-a quick and dirty usability scale. Usability Evaluation Industry 189(194), 4–7 (1996)

    Google Scholar 

  4. Chen, M., Jin, Y., Goodall, T., Yu, X., Bovik, A.C.: Study of 3d virtual reality picture quality. IEEE J. Selected Topics Signal Process. 14(1), 89–102 (2019)

    Article  Google Scholar 

  5. Croce, V., Caroti, G., De Luca, L., Piemonte, A., Véron, P.: Neural radiance fields (nerf): review and potential applications to digital cultural heritage. Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci. 48, 453–460 (2023)

    Article  Google Scholar 

  6. Deng, C., et al.: Nerdi: Single-view nerf synthesis with language-guided diffusion as general image priors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20637–20647 (2023)

    Google Scholar 

  7. European Commission: Cultural heritage and cultural and creative industries (ccis). https://research-and-innovation.ec.europa.eu/research-area/social-sciences-and-humanities/cultural-heritage-and-cultural-and-creative-industries-ccis_en (Year of access), Accessed 17 March 2024

  8. Fangi, G., Wahbeh, W., Malinverni, E.S., Di Stefano, F., Pierdicca, R.: Documentation of syrian lost heritage: From 3d reconstruction to open information system (2022)

    Google Scholar 

  9. Gao, K., Gao, Y., He, H., Lu, D., Xu, L., Li, J.: Nerf: Neural radiance field in 3d vision, a comprehensive review. arXiv preprint arXiv:2210.00379 (2022)

  10. Guédon, A., Lepetit, V.: Sugar: Surface-aligned gaussian splatting for efficient 3d mesh reconstruction and high-quality mesh rendering. arXiv preprint arXiv:2311.12775 (2023)

  11. Hart, S.G., Staveland, L.E.: Development of nasa-tlx (task load index): results of empirical and theoretical research. In: Advances in psychology, vol. 52, pp. 139–183. Elsevier (1988)

    Google Scholar 

  12. Hily, A., Dupont, L., Arbelaez-Garces, G., Camargo, M., Dinet, J.: Evaluation and validation process of extended reality applications developed in an industrial context: a systematic review. SN Comput. Sci. 4(5), 637 (2023)

    Article  Google Scholar 

  13. Hirzle, T., Müller, F., Draxler, F., Schmitz, M., Knierim, P., Hornbæk, K.: When xr and ai meet-a scoping review on extended reality and artificial intelligence. In: Proceedings of the 2023 CHI Conference on Human Factors in ComputingmSystems, pp. 1–45 (2023)

    Google Scholar 

  14. Holzwarth, V., Gisler, J., Hirt, C., Kunz, A.: Comparing the accuracy and precision of steamvr tracking 2.0 and oculus quest 2 in a room scale setup. In: Proceedings of the 2021 5th International Conference on Virtual and Augmented Reality Simulations, pp. 42–46 (2021)

    Google Scholar 

  15. Huynh-The, T., Pham, Q.V., Pham, X.Q., Nguyen, T.T., Han, Z., Kim, D.S.: Artificial intelligence for the metaverse: a survey. Eng. Appl. Artif. Intell. 117, 105581 (2023)

    Article  Google Scholar 

  16. Jin, Y., Chen, M., Goodall, T., Patney, A., Bovik, A.C.: Subjective and objective quality assessment of 2d and 3d foveated video compression in virtual reality. IEEE Trans. Image Process. 30, 5905–5919 (2021)

    Article  Google Scholar 

  17. Kerbl, B., Kopanas, G., Leimkühler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023)

    Google Scholar 

  18. Li, B., Xu, X., Tang, S., Yu, L., Wang, Z.: Human perception-guided meta-training for few-shot nerf. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 13206–13210. IEEE (2024)

    Google Scholar 

  19. Li, K., Schmidt, S., Rolff, T., Bacher, R., Leemans, W., Steinicke, F.: Magic nerf lens: interactive fusion of neural radiance fields for virtual facility inspection. Front. Virtual Reality 5, 1377245 (2024)

    Article  Google Scholar 

  20. Li, Z., et al.: Neuralangelo: high-fidelity neural surface reconstruction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8456–8465 (2023)

    Google Scholar 

  21. Li, Z., Zhang, Y., Wu, C., Zhu, J., Zhang, L.: Ho-gaussian: Hybrid optimization of 3d gaussian splatting for urban scenes. arXiv preprint arXiv:2403.20032 (2024)

  22. Liang, H., Wu, T., Hanji, P., Banterle, F., Gao, H., Mantiuk, R., Oztireli, C.: Perceptual quality assessment of nerf and neural view synthesis methods for front-facing views. arXiv preprint arXiv:2303.15206 (2023)

  23. Long, X., et al.: Wonder3d: Single image to 3d using cross-domain diffusion. arXiv preprint arXiv:2310.15008 (2023)

  24. Martin, P., Rodrigues, A., Ascenso, J., Queluz, M.P.: Nerf-qa: neural radiance fields quality assessment database. In: 2023 15th International Conference on Quality of Multimedia Experience (QoMEX), pp. 107–110. IEEE (2023)

    Google Scholar 

  25. Mazzacca, G., et al.: Nerf for heritage 3d reconstruction. Inter. Archiv. Photogrammetry, Remote Sensing Spatial Inform. Sci. 48(M-2-2023), 1051–1058 (2023)

    Google Scholar 

  26. Meng, X., Chen, W., Yang, B.: Neat: learning neural implicit surfaces with arbitrary topologies from multi-view images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 248–258 (2023)

    Google Scholar 

  27. 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 

  28. Nagta, A., Sharma, B., Sharma, A., et al.: Oculus: a new dimension to virtual reality. In: 2022 International Conference on Automation, Computing and Renewable Systems (ICACRS), pp. 1169–1172. IEEE (2022)

    Google Scholar 

  29. Nehmé, Y., Dupont, F., Farrugia, J.P., Le Callet, P., Lavoué, G.: Visual quality of 3d meshes with diffuse colors in virtual reality: subjective and objective evaluation. IEEE Trans. Visual Comput. Graph. 27(3), 2202–2219 (2020)

    Article  Google Scholar 

  30. Onuoha, C., Flaherty, J.A., Luo, S., Huong, T.T., Thang, T.C.: An evaluation of quality metrics for neural radiance field. In: 2023 IEEE 15th International Conference on Computational Intelligence and Communication Networks (CICN), pp. 619–623. IEEE (2023)

    Google Scholar 

  31. Pepe, M., Alfio, V.S., Costantino, D.: Assessment of 3d model for photogrammetric purposes using ai tools based on nerf algorithm. Heritage 6(8), 5719–5731 (2023)

    Article  Google Scholar 

  32. Perez-Ortiz, M., Mikhailiuk, A., Zerman, E., Hulusic, V., Valenzise, G., Mantiuk, R.K.: From pairwise comparisons and rating to a unified quality scale. IEEE Trans. Image Process. 29, 1139–1151 (2019)

    Article  MathSciNet  Google Scholar 

  33. Picardi, A., Caruso, G.: User-centered evaluation framework to support the interaction design for augmented reality applications. Multimodal Technol. Interact. 8(5), 41 (2024)

    Article  Google Scholar 

  34. Qu, Q., Liang, H., Chen, X., Chung, Y.Y., Shen, Y.: Nerf-nqa: no-reference quality assessment for scenes generated by nerf and neural view synthesis methods. IEEE Trans. Visualizat. Comput. Graph. (2024)

    Google Scholar 

  35. Qureshi, A.H., Alaloul, W.S., Murtiyoso, A., Saad, S., Manzoor, B.: Comparison of photogrammetry tools considering rebar progress recognition. Intern. Archiv. Photogrammetry, Remote Sensing Spatial Inform. Sci. 43, 141–146 (2022)

    Article  Google Scholar 

  36. Scorolli, C., Grasso, E.N., Stacchio, L., Armandi, V., Matteucci, G., Marfia, G.: Would you rather come to a tango concert in theater or in vr? aesthetic emotions & social presence in musical experiences, either live, 2d or 3d. Computers in Human Behavior, p. 107910 (2023)

    Google Scholar 

  37. Series, B.: Methodology for the subjective assessment of the quality of television pictures. Recommendation ITU-R BT 500(13) (2012)

    Google Scholar 

  38. Speicher, M., Cucerca, S., Krüger, A.: Vrshop: a mobile interactive virtual reality shopping environment combining the benefits of on-and offline shopping. Proc. ACM Interact. Mobile, Wearable Ubiquitous Technol. 1(3), 1–31 (2017)

    Article  Google Scholar 

  39. Stacchio, L., Scorolli, C., Marfia, G.: Evaluating human aesthetic and emotional aspects of 3d generated content through extended reality (2022)

    Google Scholar 

  40. Tancik, M., et al.: Nerfstudio: a modular framework for neural radiance field development. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1–12 (2023)

    Google Scholar 

  41. Teruggi, S., Grilli, E., Fassi, F., Remondino, F.: 3d surveying, semantic enrichment and virtual access of large cultural heritage. ISPRS Annals Photogrammetry, Remote Sensing Spatial Inform. Sci. 8, 155–162 (2021)

    Article  Google Scholar 

  42. Tewari, A., et al.: State of the art on neural rendering. In: Computer Graphics Forum, vol. 39, pp. 701–727. Wiley Online Library (2020)

    Google Scholar 

  43. Tosi, F., et al.: How nerfs and 3d gaussian splatting are reshaping slam: a survey. arXiv preprint arXiv:2402.13255 (2024)

  44. Venkatesh, V., Bala, H.: Technology acceptance model 3 and a research agenda on interventions. Decis. Sci. 39(2), 273–315 (2008)

    Article  Google Scholar 

  45. Wang, Y., et al.: A survey on metaverse: Fundamentals, security, and privacy. IEEE Commun. Surv. Tutorials (2022)

    Google Scholar 

  46. Yu, Z., et al.: Sdfstudio: A unified framework for surface reconstruction (2022)

    Google Scholar 

  47. Zerman, E., Hulusic, V., Valenzise, G., Mantiuk, R.K., Dufaux, F.: The relation between mos and pairwise comparisons and the importance of cross-content comparisons. Electronic Imaging 30, 1–6 (2018)

    Article  Google Scholar 

Download references

Acknowledgements

This work has been funded by the European Union - NextGenerationEU under the Italian Ministry of University and Research (MUR) National Innovation Ecosystem grant ECS00000041 - VITALITY - CUP D83C22000710005.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Lorenzo Stacchio .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2024 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

Stacchio, L., Balloni, E., Gorgoglione, L., Paolanti, M., Frontoni, E., Pierdicca, R. (2024). X-NR: Towards An Extended Reality-Driven Human Evaluation Framework for Neural-Rendering. In: De Paolis, L.T., Arpaia, P., Sacco, M. (eds) Extended Reality. XR Salento 2024. Lecture Notes in Computer Science, vol 15027. Springer, Cham. https://doi.org/10.1007/978-3-031-71707-9_25

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-71707-9_25

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-71706-2

  • Online ISBN: 978-3-031-71707-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics