Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916863360892928 |
|---|---|
| author | Qin, Guanyi Wang, Ziyue Shen, Daiyun Liu, Haofeng Zhou, Hantao Wu, Junde Hu, Runze Jin, Yueming |
| author_facet | Qin, Guanyi Wang, Ziyue Shen, Daiyun Liu, Haofeng Zhou, Hantao Wu, Junde Hu, Runze Jin, Yueming |
| contents | Given an object mask, Semi-supervised Video Object Segmentation (SVOS) technique aims to track and segment the object across video frames, serving as a fundamental task in computer vision. Although recent memory-based methods demonstrate potential, they often struggle with scenes involving occlusion, particularly in handling object interactions and high feature similarity. To address these issues and meet the real-time processing requirements of downstream applications, in this paper, we propose a novel bOundary Amendment video object Segmentation method with Inherent Structure refinement, hereby named OASIS. Specifically, a lightweight structure refinement module is proposed to enhance segmentation accuracy. With the fusion of rough edge priors captured by the Canny filter and stored object features, the module can generate an object-level structure map and refine the representations by highlighting boundary features. Evidential learning for uncertainty estimation is introduced to further address challenges in occluded regions. The proposed method, OASIS, maintains an efficient design, yet extensive experiments on challenging benchmarks demonstrate its superior performance and competitive inference speed compared to other state-of-the-art methods, i.e., achieving the F values of 91.6 (vs. 89.7 on DAVIS-17 validation set) and G values of 86.6 (vs. 86.2 on YouTubeVOS 2019 validation set) while maintaining a competitive speed of 48 FPS on DAVIS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18944 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation Qin, Guanyi Wang, Ziyue Shen, Daiyun Liu, Haofeng Zhou, Hantao Wu, Junde Hu, Runze Jin, Yueming Computer Vision and Pattern Recognition Image and Video Processing Given an object mask, Semi-supervised Video Object Segmentation (SVOS) technique aims to track and segment the object across video frames, serving as a fundamental task in computer vision. Although recent memory-based methods demonstrate potential, they often struggle with scenes involving occlusion, particularly in handling object interactions and high feature similarity. To address these issues and meet the real-time processing requirements of downstream applications, in this paper, we propose a novel bOundary Amendment video object Segmentation method with Inherent Structure refinement, hereby named OASIS. Specifically, a lightweight structure refinement module is proposed to enhance segmentation accuracy. With the fusion of rough edge priors captured by the Canny filter and stored object features, the module can generate an object-level structure map and refine the representations by highlighting boundary features. Evidential learning for uncertainty estimation is introduced to further address challenges in occluded regions. The proposed method, OASIS, maintains an efficient design, yet extensive experiments on challenging benchmarks demonstrate its superior performance and competitive inference speed compared to other state-of-the-art methods, i.e., achieving the F values of 91.6 (vs. 89.7 on DAVIS-17 validation set) and G values of 86.6 (vs. 86.2 on YouTubeVOS 2019 validation set) while maintaining a competitive speed of 48 FPS on DAVIS. |
| title | Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2507.18944 |