Continuous Representation Methods, Theories, and Applications: An Overview and Perspectives

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Luo, Yisi, Zhao, Xile, Meng, Deyu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910961112186880
author Luo, Yisi
Zhao, Xile
Meng, Deyu
author_facet Luo, Yisi
Zhao, Xile
Meng, Deyu
contents Recently, continuous representation methods emerge as novel paradigms that characterize the intrinsic structures of real-world data through function representations that map positional coordinates to their corresponding values in the continuous space. As compared with the traditional discrete framework, the continuous framework demonstrates inherent superiority for data representation and reconstruction (e.g., image restoration, novel view synthesis, and waveform inversion) by offering inherent advantages including resolution flexibility, cross-modal adaptability, inherent smoothness, and parameter efficiency. In this review, we systematically examine recent advancements in continuous representation frameworks, focusing on three aspects: (i) Continuous representation method designs such as basis function representation, statistical modeling, tensor function decomposition, and implicit neural representation; (ii) Theoretical foundations of continuous representations such as approximation error analysis, convergence property, and implicit regularization; (iii) Real-world applications of continuous representations derived from computer vision, graphics, bioinformatics, and remote sensing. Furthermore, we outline future directions and perspectives to inspire exploration and deepen insights to facilitate continuous representation methods, theories, and applications. All referenced works are summarized in our open-source repository: https://github.com/YisiLuo/Continuous-Representation-Zoo
format Preprint
id arxiv_https___arxiv_org_abs_2505_15222
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continuous Representation Methods, Theories, and Applications: An Overview and Perspectives
Luo, Yisi
Zhao, Xile
Meng, Deyu
Computer Vision and Pattern Recognition
Recently, continuous representation methods emerge as novel paradigms that characterize the intrinsic structures of real-world data through function representations that map positional coordinates to their corresponding values in the continuous space. As compared with the traditional discrete framework, the continuous framework demonstrates inherent superiority for data representation and reconstruction (e.g., image restoration, novel view synthesis, and waveform inversion) by offering inherent advantages including resolution flexibility, cross-modal adaptability, inherent smoothness, and parameter efficiency. In this review, we systematically examine recent advancements in continuous representation frameworks, focusing on three aspects: (i) Continuous representation method designs such as basis function representation, statistical modeling, tensor function decomposition, and implicit neural representation; (ii) Theoretical foundations of continuous representations such as approximation error analysis, convergence property, and implicit regularization; (iii) Real-world applications of continuous representations derived from computer vision, graphics, bioinformatics, and remote sensing. Furthermore, we outline future directions and perspectives to inspire exploration and deepen insights to facilitate continuous representation methods, theories, and applications. All referenced works are summarized in our open-source repository: https://github.com/YisiLuo/Continuous-Representation-Zoo
title Continuous Representation Methods, Theories, and Applications: An Overview and Perspectives
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.15222