Neural Radiance Fields Convert 2D to 3D Texture
DOI:
https://doi.org/10.5281/zenodo.12200107Keywords:
texture, 2d images, 3d images, neural radianceAbstract
The objective of our project is to capture pictures or videos by surrounding a circle of objects, such as chairs, tables, cars, and more.[1]Utilizing advanced 3D reconstruction technology, we aim to generate 3D models of these captured objects. Post reconstruction, these 3D models can be edited through an intuitive interface, enabling users to apply different textures and make other modifications. This project has significant applications in various domains such as home decoration, vehicle customization, and beyond. For the 3D reconstruction in this project, we employed Nvidia's latest ngp-instant method, which leverages hash encoding for 3D graphics reconstruction. This technique offers a faster inference speed compared to traditional NeRF (Neural Radiance Fields). Following the 3D reconstruction, we apply volume rendering to visualize the 3D models. To facilitate user editability[2], we integrated an editable interface inspired by StyleGAN, utilizing a texture loss function to transform the 3D model into a customizable texture. This combination of technologies allows for a seamless and efficient process in creating and editing 3D models from 2D images.
Downloads
References
Li, Zhenglin, et al. (2023). Stock market analysis and prediction using LSTM: A case study on technology stocks. Innovations in Applied Engineering and Technology (2023), 1-6.
Hong, Bo, et al. (2024). The application of artificial intelligence technology in assembly techniques within the industrial sector. Journal of Artificial Intelligence General Science (JAIGS), 5(1), 1-12.
Zhou, Chang, et al. (2024). Optimizing search advertising strategies: Integrating reinforcement learning with generalized second-price auctions for enhanced ad ranking and bidding. arXiv preprint arXiv:2405.13381.
Li, Shaojie, Yuhong Mo, & Zhenglin Li. (2022). Automated pneumonia detection in chest x-ray images using deep learning model. Innovations in Applied Engineering and Technology, 1-6.
Zhou, Chang, et al. (2024). Optimizing search advertising strategies: Integrating reinforcement learning with generalized second-price auctions for enhanced ad ranking and bidding. arXiv preprint arXiv:2405.13381.
Mo, Yuhong, et al. (2024). Password complexity prediction based on roberta algorithm. Applied Science and Engineering Journal for Advanced Research, 3(3), 1-5.
Jin, Jiajun, et al. (2024). Enhancing federated semi-supervised learning with out-of-distribution filtering amidst class mismatches. Journal of Computer Technology and Applied Mathematics, 1(1), 100-108.
Dai, Shuying, et al. (2024). AI-based NLP section discusses the application and effect of bag-of-words models and TF-IDF in NLP tasks. Journal of Artificial Intelligence General science (JAIGS), 5(1), 13-21.
Mo, Yuhong, et al. (2024). Large Language Model (LLM) AI text generation detection based on transformer deep learning algorithm. International Journal of Engineering and Management Research, 14(2), 154-159.
Song, Jintong, et al. (2024). A comprehensive evaluation and comparison of enhanced learning methods. Academic Journal of Science and Technology, 10(3), 167-171.
Dai, Shuying, et al. (2024). The cloud-based design of unmanned constant temperature food delivery trolley in the context of artificial intelligence. Journal of Computer Technology and Applied Mathematics, 1(1), 6-12.
Liu, Tianrui, et al. (2024). Spam detection and classification based on distilbert deep learning algorithm. Applied Science and Engineering Journal for Advanced Research, 3(3), 6-10.
Mo, Yuhong, et al. (2024). Make scale invariant feature transform “Fly” with CUDA. International Journal of Engineering and Management Research, 14(3), 38-45.
He, Shuyao, et al. (2024). Lidar and monocular sensor fusion depth estimation. Applied Science and Engineering Journal for Advanced Research, 3(3), 20-26.
Samir Elhedhli, Zichao Li, James, & H. Bookbinder. (2017). Airfreight forwarding under system-wide and double discounts. EURO Journal on Transportation and Logistics, 6(2), 165–83. https://doi.org/10.1007/s13676-015-0093-5.
Liu, Jihang, et al. (2024). Unraveling large language models: From evolution to ethical implications-introduction to large language models. World Scientific Research Journal, 10(5), 97-102.
Lin, Zheng, et al. (2024). Text sentiment detection and classification based on integrated learning algorithm. Applied Science and Engineering Journal for Advanced Research, 3(3), 27-33.
Zhao, Peng, et al. (2024). Task allocation planning based on hierarchical task network for national economic mobilization. Journal of Artificial Intelligence General Science, 5(1), 22-31.
Zhu, Armando, et al. (2024). Cross-task multi-branch vision transformer for facial expression and mask wearing classification. arXiv preprint arXiv:2404.14606.
Li, Keqin, et al. (2024). Utilizing deep learning to optimize software development processes. arXiv preprint arXiv:2404.13630.
Li, Keqin, et al. (2024). The application of augmented reality (ar) in remote work and education. arXiv preprint arXiv:2404.10579.
Wang, Jin, et al. (2024). Research on emotionally intelligent dialogue generation based on automatic dialogue system. arXiv preprint arXiv:2404.11447.
C. Zhou, Y. Zhao, Y. Zou, J. Cao, W. Fan, Y. Zhao, & C. Chiyu. (2024 May). Predict click-through rates with deep interest network model in e-commerce advertising.
C. Zhou, Y. Zhao, S. Liu, Y. Zhao, X. Li, & C. Cheng. (2024). Research on driver facial fatigue detection based on yolov8 model. ResearchGate.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Yang Wang, Chenghao Wang, Zichao Li, Zhuoyue Wang, Xinqi Liu, Yue Zhu
This work is licensed under a Creative Commons Attribution 4.0 International License.
