생성형 인공지능을 활용한 3D 모델 생성 성능 비교 연구
A Comparative Study on 3D Model Generation Performance Using Generative AI
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
생성형 인공지능 기술의 급속한 발전은 산업 및 일상생활 전반에 걸쳐 그 의존도를 높이고 있다. 그러나 대부분의 생성형 인공지능 솔루션은 주로 텍스트 또는 2D 이미지 생성에 중점을 두고있으며, 3D 모델 생성 분야에서는 상대적으로 연구가 부족한 상황이다. 본 연구에서는 ChatGPT, Copilot, Gemini 세 가지 생성형 AI 모델을 대상으로 3D 모델 생성 성능을 비교 분석하였다. 연구방법으로는 오픈소스 GPL 라이선스를 따르는 Blender 그래픽 제작 도구에서 사용하는 스크립트를ChatGPT, Copilot, Gemini 모델을 통해 자동 생성한 후, 각각의 성능을 정확도(Accuracy), 재현율(Recall), 정밀도(Precision), F1 점수(F1 Score) 지표로 평가하였다. 평가 결과, ChatGPT와 Copilot은우수한 성능을 보인 반면, Gemini는 상대적으로 낮은 성능을 나타냈다. 이러한 성능 차이는 3D 모델 생성과 관련한 학습 데이터의 차이에서 기인한 것으로 추정된다. 본 연구는 생성형 인공지능모델이 특정 분야에 따라 성능이 상이함을 확인하였으며, 향후 성능 향상을 위해 각 모델에 대한추가적인 학습과 업그레이드가 필요할 것으로 판단된다.
Abstract
The rapid advancement of generative AI technology has led to its increasing reliance across various industries and everyday applications. However, most generative AI solutions have focused primarily on generating text or 2D images, with relatively little attention paid to 3D model generation. This study conducts a comparative analysis of the performance of three generative AI models ChatGPT, Copilot, and Gemini in generating 3D models. The methodology involved generating scripts for use in the open-source Blender graphics tool, which operates under a GPL license, using each of the three AI models. The performance of these models was then evaluated using metrics such as Accuracy, Recall, Precision, and F1 Score. The results showed that ChatGPT and Copilot outperformed Gemini, which exhibited lower performance. This discrepancy in performance is likely due to differences in the training data related to 3D model generation. This study demonstrates that the performance of generative AI models varies significantly depending on the domain of application, highlighting the need for further development and upgrades to improve their effectiveness in specific areas like 3D modeling.
참고문헌 (19)
- G. Rani, "Comparative Analysis of Generative AI Models", 2023 International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT), pp.760~765 (2023)
- M. Hollender, "Engineering Challenges in Industrial AI", 2024 IEEE, 2024, 41~42
- "IEEE Computational Intelligence Magazine", 2023, 10~12, 10.1109[DOI]
- P. Dreuw, "Confidence-Based Discriminative Training for Model Adaptation in Offline Arabic Handwriting Recognition", 2009 10th International Conference on Document Analysis and Recognition, pp.596~600 (2009)
- G. Rani, "Comparative Analysis of Generative AI Models", 2023 International Conference on Advances in Computation, Communication and Information Technology(ICAICCIT), pp.760~765 (2023)
- P. G. Shivakumar, "Discriminative Speech Recognition Rescoring With Pre-Trained Language Models", 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp.1~7 (2023)
- S. Warudkar, "Unlocking the Potential of Generative AI in Large Language Models", 2024 Parul International Conference on Engineering and Technology (PICET), pp.1~5 (2024)
- J. Hwang, "A Brief Survey of Watermarks in Generative AI", 2023 14th International Conference on Information and Communication Technology Convergence (ICTC), pp.1157~1160 (2023)
- S. G. Prasad, "Role of Artificial Intelligence based Chat Generative Pre-trained Transformer(ChatGPT)in Cyber Security", 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), pp.107~114 (2023)
- S. -S. Chen, "Applying the Diamond Model of Intrusion Analysis with Generative Pre-trained Transformer 3", 2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan), pp.289~290 (2023)
- N. Rawal, "Enhancing Large Language Model Performance with Reinforcement Learning from Human Feedback : A Comprehensive Study on Q&A, Summarization, and Classification", 2024 International Conference on Electrical, Computer and Energy Technologies (ICECET), pp.1~6 (2024)
- Y. Cao, "Reinforcement Learning with Human Feedback for Realistic Traffic Simulation", 2024 IEEE International Conference on Robotics and Automation (ICRA), pp.14428~14434 (2024)
- X. Zhang, "Triple-Based Data Augmentation for Event Temporal Extraction via Reinforcement Learning from Human Feedback", 2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pp.1627~1632 (2024)
- H. -C. Chen, "Harnessing AI for Scientific Illustration : Exploring Tornado Dynamics Through Midjourney", 2023 12th International Conference on Awareness Science and Technology (iCAST), pp.136~141 (2023)
- A. Horváth, "Stable Diffusion with Memristive Cellular Neural Networks", 2024 IEEE International Symposium on Circuits and Systems (ISCAS), pp.1~5 (2024)
- S. S. Nair, "Redefining Creativity in Design : Exploring the Impact of AI-Generated Imagery on Design Professionals and Amateurs", 2024 11th International Conference on Computing for Sustainable Global Development (INDIACom), pp.1723~1728 (2024)
- J. Lv, "GPT4Motion : Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning", 2024 IEEE, 2024, 1430~1440
- A. Madhubalan, "Blender-GAN : Multi-Target Conditional Generative Adversarial Network for Novel Class Synthetic Data Generation", 2024 International Conference on Smart Applications, Communications and Networking (SmartNets), pp.1~7 (2024)
- A. Madhubalan, "Blender-GAN : Multi-Target Conditional Generative Adversarial Network for Novel Class Synthetic Data Generation", 2024 International Conference on Smart Applications, Communications and Networking (SmartNets), pp.1~7 (2024)