Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Daochang, Zhang, Junyu, Dinh, Anh-Dung, Park, Eunbyung, Zhang, Shichao, Mian, Ajmal, Shah, Mubarak, Xu, Chang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2501.10928
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915251153272832
author Liu, Daochang
Zhang, Junyu
Dinh, Anh-Dung
Park, Eunbyung
Zhang, Shichao
Mian, Ajmal
Shah, Mubarak
Xu, Chang
author_facet Liu, Daochang
Zhang, Junyu
Dinh, Anh-Dung
Park, Eunbyung
Zhang, Shichao
Mian, Ajmal
Shah, Mubarak
Xu, Chang
contents Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by enabling machines to create and interpret visual data with unprecedented sophistication. This transformation builds upon a foundation of generative models to produce realistic images, videos, and 3D/4D content. Conventional generative models primarily focus on visual fidelity while often neglecting the physical plausibility of the generated content. This gap limits their effectiveness in applications that require adherence to real-world physical laws, such as robotics, autonomous systems, and scientific simulations. As generative models evolve to increasingly integrate physical realism and dynamic simulation, their potential to function as "world simulators" expands. Therefore, the field of physics-aware generation in computer vision is rapidly growing, calling for a comprehensive survey to provide a structured analysis of current efforts. To serve this purpose, the survey presents a systematic review, categorizing methods based on how they incorporate physical knowledge, either through explicit simulation or implicit learning. It also analyzes key paradigms, discusses evaluation protocols, and identifies future research directions. By offering a comprehensive overview, this survey aims to help future developments in physically grounded generation for computer vision. The reviewed papers are summarized at https://tinyurl.com/Physics-Aware-Generation.
format Preprint
id arxiv_https___arxiv_org_abs_2501_10928
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Physical AI in Vision: A Survey
Liu, Daochang
Zhang, Junyu
Dinh, Anh-Dung
Park, Eunbyung
Zhang, Shichao
Mian, Ajmal
Shah, Mubarak
Xu, Chang
Computer Vision and Pattern Recognition
Artificial Intelligence
Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by enabling machines to create and interpret visual data with unprecedented sophistication. This transformation builds upon a foundation of generative models to produce realistic images, videos, and 3D/4D content. Conventional generative models primarily focus on visual fidelity while often neglecting the physical plausibility of the generated content. This gap limits their effectiveness in applications that require adherence to real-world physical laws, such as robotics, autonomous systems, and scientific simulations. As generative models evolve to increasingly integrate physical realism and dynamic simulation, their potential to function as "world simulators" expands. Therefore, the field of physics-aware generation in computer vision is rapidly growing, calling for a comprehensive survey to provide a structured analysis of current efforts. To serve this purpose, the survey presents a systematic review, categorizing methods based on how they incorporate physical knowledge, either through explicit simulation or implicit learning. It also analyzes key paradigms, discusses evaluation protocols, and identifies future research directions. By offering a comprehensive overview, this survey aims to help future developments in physically grounded generation for computer vision. The reviewed papers are summarized at https://tinyurl.com/Physics-Aware-Generation.
title Generative Physical AI in Vision: A Survey
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2501.10928