Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Zixuan, Li, Jiaxin, Tan, Liming, Guo, Yejie, Liang, Junxuan, Lu, Cewu, Li, Yong-Lu
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2412.13803
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915314728435712
author Chen, Zixuan
Li, Jiaxin
Tan, Liming
Guo, Yejie
Liang, Junxuan
Lu, Cewu
Li, Yong-Lu
author_facet Chen, Zixuan
Li, Jiaxin
Tan, Liming
Guo, Yejie
Liang, Junxuan
Lu, Cewu
Li, Yong-Lu
contents Intelligent robots need to interact with diverse objects across various environments. The appearance and state of objects frequently undergo complex transformations depending on the object properties, e.g., phase transitions. However, in the vision community, segmenting dynamic objects with phase transitions is overlooked. In light of this, we introduce the concept of phase in segmentation, which categorizes real-world objects based on their visual characteristics and potential morphological and appearance changes. Then, we present a new benchmark, Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (M$^3$-VOS), to verify the ability of models to understand object phases, which consists of 479 high-resolution videos spanning over 10 distinct everyday scenarios. It provides dense instance mask annotations that capture both object phases and their transitions. We evaluate state-of-the-art methods on M$^3$-VOS, yielding several key insights. Notably, current appearance-based approaches show significant room for improvement when handling objects with phase transitions. The inherent changes in disorder suggest that the predictive performance of the forward entropy-increasing process can be improved through a reverse entropy-reducing process. These findings lead us to propose ReVOS, a new plug-andplay model that improves its performance by reversal refinement. Our data and code will be publicly available at https://zixuan-chen.github.io/M-cube-VOS.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13803
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle M$^3$-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation
Chen, Zixuan
Li, Jiaxin
Tan, Liming
Guo, Yejie
Liang, Junxuan
Lu, Cewu
Li, Yong-Lu
Computer Vision and Pattern Recognition
Artificial Intelligence
Intelligent robots need to interact with diverse objects across various environments. The appearance and state of objects frequently undergo complex transformations depending on the object properties, e.g., phase transitions. However, in the vision community, segmenting dynamic objects with phase transitions is overlooked. In light of this, we introduce the concept of phase in segmentation, which categorizes real-world objects based on their visual characteristics and potential morphological and appearance changes. Then, we present a new benchmark, Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (M$^3$-VOS), to verify the ability of models to understand object phases, which consists of 479 high-resolution videos spanning over 10 distinct everyday scenarios. It provides dense instance mask annotations that capture both object phases and their transitions. We evaluate state-of-the-art methods on M$^3$-VOS, yielding several key insights. Notably, current appearance-based approaches show significant room for improvement when handling objects with phase transitions. The inherent changes in disorder suggest that the predictive performance of the forward entropy-increasing process can be improved through a reverse entropy-reducing process. These findings lead us to propose ReVOS, a new plug-andplay model that improves its performance by reversal refinement. Our data and code will be publicly available at https://zixuan-chen.github.io/M-cube-VOS.github.io/.
title M$^3$-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.13803