Physics-Informed Guided Disentanglement in Generative Networks

Pizzati, Fabio; Cerri, Pietro; Charette, Raoul de

doi:10.1109/tpami.2023.3257486

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Book1

Other1

Article1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal

Jin,

Li,

Wang

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal

Jin,

Li,

Wang

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Time to Shine: Fine-Tuning Object Detection Models with Synthetic Adverse Weather Images

Rothmeier,

Huber,

Knoll

2024

2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Physics-Informed Computer Vision: A Review and Perspectives

Banerjee,

Nguyen,

Fookes

et al. 2024

ACM Comput. Surv.

View full text Add to dashboard Cite

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.

show abstract

Physics-Informed Guided Disentanglement in Generative Networks

Cited by 3 publications

References 79 publications

Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal

Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal

Time to Shine: Fine-Tuning Object Detection Models with Synthetic Adverse Weather Images

Physics-Informed Computer Vision: A Review and Perspectives

Contact Info

Product

Resources

About