融合SAM2与Cutie优势，提升视频目标分割精度与稳定性。
Enriched Feature Representation and Motion Prediction Module for MOSEv2 Track of 7th LSVOS Challenge: 3rd Place Solution
- 用SAM2的ViT编码器替换Cutie的主干，增强特征表达能力。
- 引入运动预测模块，显著提升时序一致性，提升分割稳定性。
- 集成三模型方案，获7th LSVOS挑战赛MOSEv2赛道第3名。
视频对象分割（VOS）是具有广泛应用的关键任务，如视频编辑和自动驾驶。尽管Cutie在基于查询的分割上表现优异，而SAM2通过预训练ViT编码器提供丰富特征表示，但两者在特征容量和时序建模方面仍存在局限。本文提出一种框架，将Cutie的编码器替换为SAM2的ViT编码器，并引入运动预测模块以增强时序稳定性。进一步采用融合Cutie、SAM2及本方案变体的集成策略，在第7届LSVOS挑战赛的MOSEv2赛道中取得第3名。最终模型命名为SCOPE（SAM2-CUTIE Object Prediction Ensemble），验证了丰富特征表示与运动预测对鲁棒视频对象分割的有效性。代码已公开于https://github.com/2025-LSVOS-3rd-place/MOSEv2_3rd_place。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。