지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 발행연도
- 2024.6
- 수록면
- 2,699 - 2,703 (5page)
이용수
초록· 키워드
오류제보하기
The field of computer vision has seen remarkable advancements in the domain of generative tasks. These advancements have facilitated the creation of diverse images from complex input data. However, traditional data-driven generative models often fall short in terms of robustness and interpretability, particularly when faced with the challenges of high-dimensional image data and noisy or insufficient training datasets. These limitations are especially problematic in tasks requiring the simulation of physical phenomena, as these models typically generate outputs that may not be physically plausible.
Physics-Informed Neural Networks (PINNs) have emerged as a potent solution to these deficiencies, integrating physical laws directly into the learning process to enhance both the accuracy and generalizability of model predictions. This paper explores the application of PINNs in various computer vision generation tasks, highlighting their utility in generating visually plausible content that adheres to realistic physical constraints. This review explores how incorporating physical laws into GANs and DDPMs, as illustrated in various research studies, addresses the shortcomings of traditional generative models, facilitating more dependable and physically accurate visual simulations across a range of applications. The merging of physics and machine learning in these instances not only stabilizes the training processes but also enhances the fidelity and robustness of generated images. Such insights underscore the broad potential of physics-informed methodologies in advancing computational vision systems, showing that these approaches are instrumental in refining the capabilities of generative models.
Physics-Informed Neural Networks (PINNs) have emerged as a potent solution to these deficiencies, integrating physical laws directly into the learning process to enhance both the accuracy and generalizability of model predictions. This paper explores the application of PINNs in various computer vision generation tasks, highlighting their utility in generating visually plausible content that adheres to realistic physical constraints. This review explores how incorporating physical laws into GANs and DDPMs, as illustrated in various research studies, addresses the shortcomings of traditional generative models, facilitating more dependable and physically accurate visual simulations across a range of applications. The merging of physics and machine learning in these instances not only stabilizes the training processes but also enhances the fidelity and robustness of generated images. Such insights underscore the broad potential of physics-informed methodologies in advancing computational vision systems, showing that these approaches are instrumental in refining the capabilities of generative models.
목차
Abstract
Ⅰ. Introduction
Ⅱ. Generative Models in Vision
Ⅲ. Physics-Informed Neural Networks in Vision Generation Tasks
Ⅳ. Conclusion
Reference
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Physics-informed Neural Networks
대한기계학회 춘추학술대회
2022 .05
-
Digital Transformation 을 위한 PINN(Physics-informed Neural Network)의 효용성 및 Feasibility Test
대한기계학회 춘추학술대회
2022 .05
-
물리기반 인공지능 기법에 의한 고분해능 실험데이터 예측
한국가시화정보학회 학술발표대회 논문집
2021 .05
-
산업에 적용 가능한 인공지능 기술: 물리지식기반 신경망
한국트라이볼로지학회 학술대회
2022 .04
-
효율적인 개념설계를 위한 물리 기반 생성 설계 프레임워크
대한기계학회 춘추학술대회
2024 .11
-
물리 정보 신경망을 이용한 TV 패키징 구조물 설계 기술 개발
대한기계학회 춘추학술대회
2024 .11
-
Physics-Based State of Charge and Energy Estimation Framework Using Physics-Informed Deep Learning Model
대한산업공학회 추계학술대회 논문집
2024 .10
-
1차원 파동 방정식 풀이를 위한 물리지식기반 인공신경망 개선
대한기계학회 춘추학술대회
2022 .11
-
PINN과 상용 소프트웨어의 2차원 유동해석 비교
한국전산유체공학회지
2024 .12
-
물리 기반 인공신경망을 이용한 수중 음파 전달 해석
대한기계학회 춘추학술대회
2024 .11
-
Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural network
Nuclear Engineering and Technology
2023 .06
-
Physics-Informed Neural Networks-based Model Predictive Control for Automated Surface Vessels
제어로봇시스템학회 국제학술대회 논문집
2024 .10
-
Hybrid Modeling Using Physics-Informed Neural Networks for Mammalian Cell Culture Prediction
한국생물공학회 학술대회
2022 .09
-
Physics-Informed Neural Network for Solving Fluid Dynamic Problems
대한기계학회 춘추학술대회
2020 .12
-
물리정보신경망 기반 멤리스터 노이즈 모델링
대한전자공학회 학술대회
2024 .06
-
실내 온도 예측을 위한 물리 정보 신경망 · 도메인 지식 통합모델 개발
대한건축학회 학술발표대회 논문집
2024 .10
-
Physics-informed neural network for heat transfer problem with cylindrical heat sources in battery pack geometry
제어로봇시스템학회 국제학술대회 논문집
2024 .10
-
혼돈 시스템에서의 PINN 학습 개선을 위한 적응형 도메인 분해
대한기계학회 춘추학술대회
2024 .11
-
물리정보 신경망을 이용한 희소 및 잡음 속도 데이터 재구성
한국가시화정보학회 학술발표대회 논문집
2023 .11
-
Physics-Informed Neural Networks for Predictive Modeling of Fatigue Delamination Growth in Composites
대한기계학회 춘추학술대회
2024 .11
최근 본 자료
댓글(0)
0