https://vilab.team/tag/%E8%A7%86%E9%A2%91%E5%AF%B9%E8%B1%A1%E5%88%86%E5%89%B2/ 视频对象分割 Hugo Blox Builder (https://hugoblox.com)en-usSun, 27 Oct 2024 00:00:00 +0000 https://vilab.team/media/icon_hu2896232876136423579.png https://vilab.team/tag/%E8%A7%86%E9%A2%91%E5%AF%B9%E8%B1%A1%E5%88%86%E5%89%B2/ https://vilab.team/publication/semantic-enhanced-point-box-joint-prompting-for-video-object/ Sun, 27 Oct 2024 00:00:00 +0000 https://vilab.team/publication/semantic-enhanced-point-box-joint-prompting-for-video-object/ <p>本文提出基于SAM的语义增强点框联合提示框架SAM-SPB，用于视频对象分割。该框架通过点跟踪分支维持对象局部结构信息，并利用语义感知的基于记忆的框跟踪分支跨帧传播对象语义一致性，从而结合局部与全局线索实现鲁棒分割。在主流VOS基准上取得了领先性能，验证了点框联合提示相比仅用点提示的优势。</p>