论文标题
带有深度运动建模的区域知识视频对象细分
Region Aware Video Object Segmentation with Deep Motion Modeling
论文作者
论文摘要
当前的半监督视频对象分割（VOS）方法通常利用一个框架的整个功能来预测对象掩码和更新内存。这引入了重要的冗余计算。为了减少冗余，我们提出了一种区域意识到的视频对象细分（RAVO）方法，该方法可以预测感兴趣的区域（ROI），以进行有效的对象分割和内存存储。 Ravos包括一个快速对象运动跟踪器，可以在下一个帧中预测其ROI。为了有效的分割，根据ROI提取对象特征，并且对象解码器设计用于对象级分割。为了有效的内存存储，我们建议运动路径内存来通过记住两个帧之间对象的运动路径中的特征来滤除冗余上下文。除了Ravos，我们还提出了一个称为OVO的大型数据集，以基准在遮挡下基准VOS模型的性能。对戴维斯和YouTube-VOS基准测试和我们的新OVO数据集的评估表明，我们的方法以更快的推理时间来实现最先进的性能，例如，戴维斯的42 fps的86.1 J＆F在YouTube-Vos上的42 fps和84.4 J＆F时，在23 fps上。
Current semi-supervised video object segmentation (VOS) methods usually leverage the entire features of one frame to predict object masks and update memory. This introduces significant redundant computations. To reduce redundancy, we present a Region Aware Video Object Segmentation (RAVOS) approach that predicts regions of interest (ROIs) for efficient object segmentation and memory storage. RAVOS includes a fast object motion tracker to predict their ROIs in the next frame. For efficient segmentation, object features are extracted according to the ROIs, and an object decoder is designed for object-level segmentation. For efficient memory storage, we propose motion path memory to filter out redundant context by memorizing the features within the motion path of objects between two frames. Besides RAVOS, we also propose a large-scale dataset, dubbed OVOS, to benchmark the performance of VOS models under occlusions. Evaluation on DAVIS and YouTube-VOS benchmarks and our new OVOS dataset show that our method achieves state-of-the-art performance with significantly faster inference time, e.g., 86.1 J&F at 42 FPS on DAVIS and 84.4 J&F at 23 FPS on YouTube-VOS.
