Physics-Informed Computer Vision: A Review and Perspectives
ACM Computing Surveys · 31.01.2025 · 57 (1) · 1-38
DOI: 10.1145/3689037 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 07.10.2024. Verfasst von Chayan Banerjee und 3 weiteren Autor:innen. Die Arbeit wurde bisher 87-mal zitiert (Crossref) und nennt 263 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Advance Queensland Industry Research Fellowship.
Abstract (Originalsprache)
The incorporation of physical information in machine learning frameworks is opening and transforming many application domains. Here the learning process is augmented through the induction of fundamental knowledge and governing physical laws. In this work, we explore their utility for computer vision tasks in interpreting and understanding visual data. We present a systematic literature review of more than 250 papers on formulation and approaches to computer vision tasks guided by physical laws. We begin by decomposing the popular computer vision pipeline into a taxonomy of stages and investigate approaches to incorporate governing physical equations in each stage. Existing approaches are analyzed in terms of modeling and formulation of governing physical processes, including modifying input data (observation bias), network architectures (inductive bias), and training losses (learning bias). The taxonomy offers a unified view of the application of the physics-informed capability, highlighting where physics-informed learning has been conducted and where the gaps and opportunities are. Finally, we highlight open problems and challenges to inform future research. While still in its early days, the study of physics-informed computer vision has the promise to develop better computer vision models that can improve physical plausibility, accuracy, data efficiency, and generalization in increasingly realistic applications.
Förderung
- Advance Queensland Industry Research Fellowship
Zitieren
APA
Banerjee, C., Nguyen, K., Fookes, C., & George, K. (2025). Physics-Informed Computer Vision: A Review and Perspectives. ACM Computing Surveys, 57(1), 1-38. https://doi.org/10.1145/3689037
Vancouver
Banerjee C, Nguyen K, Fookes C, George K. Physics-Informed Computer Vision: A Review and Perspectives. ACM Computing Surveys. 2025;57(1):1-38. doi:10.1145/3689037
BibTeX
@article{Banerjee2025,
author = {Banerjee, Chayan and Nguyen, Kien and Fookes, Clinton and George, Karniadakis},
title = {Physics-Informed Computer Vision: A Review and Perspectives},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {1},
pages = {1--38},
doi = {10.1145/3689037}
}
EUVIMED