Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lim, Chang Soo, Moon, Joonyoung, Cho, Donghyeon
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.15781
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909797625888768
author Lim, Chang Soo
Moon, Joonyoung
Cho, Donghyeon
author_facet Lim, Chang Soo
Moon, Joonyoung
Cho, Donghyeon
contents Video object segmentation (VOS) is a challenging task with wide applications such as video editing and autonomous driving. While Cutie provides strong query-based segmentation and SAM2 offers enriched representations via a pretrained ViT encoder, each has limitations in feature capacity and temporal modeling. In this report, we propose a framework that integrates their complementary strengths by replacing the encoder of Cutie with the ViT encoder of SAM2 and introducing a motion prediction module for temporal stability. We further adopt an ensemble strategy combining Cutie, SAM2, and our variant, achieving 3rd place in the MOSEv2 track of the 7th LSVOS Challenge. We refer to our final model as SCOPE (SAM2-CUTIE Object Prediction Ensemble). This demonstrates the effectiveness of enriched feature representation and motion prediction for robust video object segmentation. The code is available at https://github.com/2025-LSVOS-3rd-place/MOSEv2_3rd_place.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15781
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enriched Feature Representation and Motion Prediction Module for MOSEv2 Track of 7th LSVOS Challenge: 3rd Place Solution
Lim, Chang Soo
Moon, Joonyoung
Cho, Donghyeon
Computer Vision and Pattern Recognition
Video object segmentation (VOS) is a challenging task with wide applications such as video editing and autonomous driving. While Cutie provides strong query-based segmentation and SAM2 offers enriched representations via a pretrained ViT encoder, each has limitations in feature capacity and temporal modeling. In this report, we propose a framework that integrates their complementary strengths by replacing the encoder of Cutie with the ViT encoder of SAM2 and introducing a motion prediction module for temporal stability. We further adopt an ensemble strategy combining Cutie, SAM2, and our variant, achieving 3rd place in the MOSEv2 track of the 7th LSVOS Challenge. We refer to our final model as SCOPE (SAM2-CUTIE Object Prediction Ensemble). This demonstrates the effectiveness of enriched feature representation and motion prediction for robust video object segmentation. The code is available at https://github.com/2025-LSVOS-3rd-place/MOSEv2_3rd_place.
title Enriched Feature Representation and Motion Prediction Module for MOSEv2 Track of 7th LSVOS Challenge: 3rd Place Solution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.15781