A Survey of Algorithms Involved in the Conversion of 2-D Images to 3-D Model

Article Sidebar

Block Diagram for methodology implemented for survey.
PDF
Published: Jun 12, 2023
DOI: https://doi.org/10.17762/ijritcc.v11i6s.6942
Keywords:
2-D image, 3-D model, SFM, SFS, MVS, PIFu, Machine learning

Main Article Content

Gopal D. Upadhye
Department of Computer Engineering, Vishwakarma Institute of Technology, Pune Pune, India
Anant Kaulage
Department of Computer Engineering, Vishwakarma Institute of Technology, Pune Pune, India
Ranjeetsingh S. Suryawanshi
Department of Computer Engineering, Vishwakarma Institute of Technology, Pune Pune, India
Roopal Tatiwar
Department of Computer Engineering, Vishwakarma Institute of Technology, Pune Pune, India
Rishikesh Unawane
Department of Computer Engineering, Vishwakarma Institute of Technology, Pune Pune, India
Aditya Taware
Department of Computer Engineering, Vishwakarma Institute of Technology, Pune Pune, India
Aryaman Todkar
Department of Computer Engineering, Vishwakarma Institute of Technology, Pune Pune, India

Abstract

Since the advent of machine learning, deep neural networks, and computer graphics, the field of 2D image to 3D model conversion has made tremendous strides. As a result, many algorithms and methods for converting 2D to 3D images have been developed, including SFM, SFS, MVS, and PIFu. Several strategies have been compared, and it was found that each has pros and cons that make it appropriate for particular applications. For instance, SFM is useful for creating realistic 3D models from a collection of pictures, whereas SFS is best for doing so from a single image. While PIFu can create extremely detailed 3D models of human figures from a single image, MVS can manage complicated situations with varied lighting and texture. The method chosen to convert 2D images to 3D ultimately depends on the demands of the application.

Article Details

How to Cite
Upadhye, G. D. ., Kaulage, A. ., Suryawanshi, R. S. ., Tatiwar, R. ., Unawane, R. ., Taware, A. ., & Todkar, A. . (2023). A Survey of Algorithms Involved in the Conversion of 2-D Images to 3-D Model. International Journal on Recent and Innovation Trends in Computing and Communication, 11(6s), 358–370. https://doi.org/10.17762/ijritcc.v11i6s.6942
Issue
Vol. 11 No. 6s (2023): Advances in Computational Modeling and Simulation of Computing Systems
Section
Articles

References

Natsume, R., Morishima, S., Kanazawa, A., and Li, H. Saito et al., 2019. Pifu: Implicit pixel-aligned function for high-resolution human digitisation in clothing. (Pp. 2304–2314) in Proceedings of the IEEE/CVF International Conference on Computer Vision.

Chan, E.R. Lin, C.Z Chan, M.A. Nagano, K. Pan, B. De Mello, S. Gallo, L.J. Guibas, J. Tremblay, S. Khamis, and T. Karras, 2022. 3D generative adversarial networks that are effective and mindful of geometry. pp. 16123–16133 in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Saito, S., Simon, T., Saragih, and Joo. Pifuhd: Multi-level implicit function with pixel alignment for high-resolution 3D human digitisation. On pages 84–93 of the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

A. Kanchan and T. Mathur, 2017. Recent developments in 2D to 3D picture conversion: a quick look at the algorithm. pp. 3480–3484 in International Research Journal of Engineering and Technology, 4(4).

S. McCann, 2015. 3D reconstruction using several pictures. Geometric and Computational Vision Lab at Stanford.

2014; Victoria M. Baretto International Journal of Engineering Research and Technology (IJERT) NCRTS - 2014 (Volume 2 - Issue 13), Automatic Learning based 2D-to-3D Image Conversion.

Wei, X., Zhang, Y., Li, Z., Fu, Y., and Xue, X. Structure from motion using deep bundle adjustment, or deepsfm. 16th European Conference on Computer Vision, Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16 (pp. 230–247). International Springer Publishing.

Moch, Kholil & Ismanto, I & Fu’ad, M. (2021). “3D reconstruction using Structure From Motion (SFM) algorithm and Multi View Stereo (MVS) based on computer vision.” ,presented in IOP Conference Series: Materials Science and Engineering. 1073. 012066. 10.1088/1757-899X/1073/1/012066.

Li and Jiwu, Chenyang and Yi, Shijie, and Li, Zixin, et al. (2019).Modeling Virtual Reality Environment Based on SFM Method . 6.179.10.2991/jrnal.k.191202.007 in Journal of Robotics, Networking, and Artificial Life.

Multi-view stereo in the "Deep Learning Era: A Comprehensive Review," Displays, Volume 70,2021, 102102, ISSN 0141-9382, by Xiang Wang, Chen Wang, Bing Liu, Xiaoqing Zhou, Liang Zhang, Jin Zheng, and Xiao Bai,

https://doi.org/10.1016/j.displa.2021.102102.

P. Gleize, W. Wang, and M. Feiszli, "SiLK--Simple Learned Keypoints" Print accessed at arXiv:2304.06194, 2023.

Wang, Z., K. Chaney, and K. Daniilidis, November 2022. "EvAC3D: From Event-Based Apparent Contours to 3D Models via Continuous Visual Hulls" 17th European Conference on Computer Vision, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VII (pp. 284–299).

Cham.Fang, Q., Song, Y., Li, K., Shen, L., Wu, H., Xiong, G. and Bo, L., 2023. Evaluate Geometry of Radiance Field with Low-frequency Color Prior. arXiv preprint arXiv:2304.04351.

S. Fang, Y. Wang, Y. Yang, X. Wu, H. Wang, W. Ding, and S. Zhou, 2023. "PVD-AL: Progressive Volume Distillation with Active Learning for Efficient Conversion Between Different NeRF Architectures". Print accessed at arXiv:2304.04012.

[14] Zhao, X., Wu, X., Chen, W., Chen, PC, Xu, Q, and Li, 2023. The phrase "ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation" Preprint available at- arXiv:2304.03608.

[15] Cao, X. Santo, F. Okura, and Y. Matsushita, 2023. The phrase "Multi-View Azimuth Stereo via Tangent Space Consistency" Preprint available at- arXiv:2303.16447.

Wang, W., Joshi, B., Burgdorfer, N., Batsos, K., Li, A.Q., Mordohai, P., and Rekleitis, 2023. The phrase "Real-Time Dense 3D Mapping of Underwater Environments" preprint available at- arXiv:2304.02704.

An, S., chen, S., zhang, K., Shi, Y., Zhu, Y., Wang, H., Song, G., Kristjansson, J., Yang, X. and Zwicker, M., 2023. “PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters”. arXiv preprint available at- arXiv:2303.14587.

Sun, Q., wang, W., Ge, Y., Mei, H., Cai, Z., et, Al. 2023. “Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction”. arXiv preprint at- arXiv:2303.13796.

tong, J., muthu, S., et. Al. (2023). “Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container”. arXiv preprint at- arXiv:2303.13805.

Wu, R., Liu, R., Tokmakov, Van Hoorick, B.,P., Zakharov, S. and Vondrick, C., (2023).” Zero-1-to-3: Zero-shot One Image to 3D Object”. arXiv preprint available at- arXiv:2303.11328.

zhang, J., Xu, B., He, Y., Qian, C. and Lin, K.Y., (2023). “Deformable Model Driven Neural Rendering for High-fidelity 3D Reconstruction of Human Heads Under Low-View Settings”. arXiv preprint, can be accessed at-arXiv:2303.13855.

Yu, Z., Huang, Fang, Breckon, et. Al. (2023). “ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction”. arXiv preprint is available at - arXiv:2303.05938.

Johnson, J., Wu, Feichtenhofer, C. Malik, J., et, Al. (2023). “Multiview Compressive Coding for 3D Reconstruction”. arXiv preprint paper available here - arXiv:2301.08247.

castle, R., Li, bian, J.W., torr, P.H. and Prisacariu, V.A., (2023). “MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices”. arXiv preprint available here- arXiv:2303.01932.

Boularias, A., Ramesh, Gan, Y. D.M., Geng, S., and chang, H. “Mono-STAR: Mono-camera Scene-level Tracking and Reconstruction”.(2023)arXiv access preprint here - arXiv:2301.13244.

cheng, Y.C., tulyakov, S., Lee, H.Y., Schwing, A. and gui, L. “SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation”.(2022) arXiv preprint available at- arXiv:2212.04493.

Guibas, L., jiang, C., Qi, C.R., yan, X., zhou, Y, Deng, C. and Anguelov, D. “NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors”. (2022). arXiv preprint available at- arXiv:2212.03267.

de Charette, R., and Cao, A.Q. “SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields”. (2022). arXiv preprint can be accessed via- arXiv:2212.02501.

Tan, Wu, T. xue, N., and xia, G.S. “NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction”.(2022). arXiv preprint available here- arXiv:2211.16799.

Jiang, Y., Xu, D., et. Al. “NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° Views”.(2022). arXiv e-prints, available here- pp.arXiv-2211.

surmann, H., et. Al.. PatchMatch-Stereo-Panorama, a fast dense reconstruction from 360 {deg} video images”.(2022) arXiv preprint available at - arXiv:2211.16266.

X. Chen, T. Jiang, J. Song, M. Rietmann, A. Geiger, M.J. Black, and O. Hilliges, 2022. "Fast-SNARF: A Neural Field Deformer for Articulated Neural Fields". arXiv:2211.15601 is an arXiv preprint.

P. Wang, L. Zhao, R. Ma, and P. Liu. "BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields",(2022). arXiv preprint: 2211.12853.

Lee, D., et. Al. (2022). “Deblurred Neural Radiance Field with Physical Scene Priors”. arXiv preprint can be accessed at- arXiv:2211.12046.

Anciukevi?ius, T., et. Al. (2022). “RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation”. arXiv preprint can be accessed at- arXiv:2211.09869.

Tombari, F., pavllo, D., rakotosaona, M.J. and tan, D.J., (2022). “Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion”. arXiv preprint available here- arXiv:2211.11674.

Azimifar, Z., along with Kamyab, S., (2022). “Deep-MDS Framework for Recovering the 3D Shape of 2D Landmarks from a Single Image”. arXiv preprint available here- arXiv:2210.15200.

Poggi, M., et. Al. (2022), October. “Multi-View Guided Multi-View Stereo”. Published in - IEEE/RSJ International Conference on Intelligent Robots and Systems .IEEE.

Koulieris, G.A., chang, Z., and shum, H.P., (November 2022). “3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models”. Publiahed in Proceedings of the 28th ACM Symposium on Virtual Reality Software and Technology (pp. 1-10).

Jiang, Y.G.,., li, H., wu, Z. and xing, Z . “Semi-supervised Single-View 3D Reconstruction via Prototype Shape Priors”. Published in Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, (October 23–27, 2022), Proceedings, Part I (pp. 535-551).

Gibson, J., Sayed, M., et.Al. “SimpleRecon: 3D reconstruction without 3D convolutions”. Published In Computer Vision–ECCV 2022: European Conference(17th edition), Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXIII (pp. 1-19)

Sun, X., Zhou, S., and Zhang, S., Xie, H., Yao, H., Sun, X., and Zhou, S.(2019). "Pix2vox: Context-aware 3d reconstruction from single and multi-view images" (Pp. 2690–2698) in Proceedings of the IEEE/CVF International Conference on Computer Vision.

Gao, C., Yu, Q., Sheng, L., Song, Y.Z., and Xu, D. "SketchSampler: Sketch-Based 3D Reconstruction via View-Dependent Depth Sampling". European Conference on Computer Vision(17th edition), Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part I (pp. 464–479). Springer Nature Switzerland, Cham.

Ayaz , M. ., & Ammad Uddin , M. . (2023). Performance Analysis of Underwater Wireless Optical Communication with Varying Salinity: Experimental Study. International Journal of Intelligent Systems and Applications in Engineering, 11(1), 18–24. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/2439

"Generalised binary search network for highly-efficient multi-view stereo" by Mi, Z., Di, C., and Xu, D., 2022. (Pages 12991–13000) in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Yang, Z., et. Al. (2022). “HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction”. arXiv preprint available at -arXiv:2206.12356.

Pumarola, A., ugrinovic, N., et. Al. “Single-view 3D Body and Cloth Reconstruction under Complex Poses”. (2022) arXiv preprint can be accessed here- arXiv:2205.04087.

Sigmund, D. tiong, L.C.O., and teoh, A.B.J. “3D-C2FT: Coarse-to-fine Transformer for Multi-view 3D Reconstruction”. (2022)Printed In Proceedings of the Asian Conference on Computer Vision (pp. 1438-1454).

Yang, Y, Z. Zheng, J. Zhu, Ji, W., and chua, T.S.“3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective”.(2022). arXiv preprint can be accessed via- arXiv:2204.13096.

Gui Shengxi et. Al. "Automated LoD-2 model reconstruction from very-high-resolution satellite-derived digital surface model and orthophoto", (2021)Proceedings of "ISPRS Journal of Photogrammetry and Remote Sensing", Volume 181, Pages 1-19, ISSN 0924-2716, https://doi.org/10.1016/j.isprsjprs.2021.08.025.

Upadhye Gopal & Kulkarni U.V. & Mane Deepak, “Improved Model Configuration Strategies for Kannada Handwritten Numeral Recognition” Image Analysis & Stereology. Vol.40, pp.181-191. 10.5566/ias.2586