PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation
This work addresses the problem of generating accurate and consistent pixel masks for objects in videos for computer vision applications, representing a strong incremental improvement over prior methods.
The authors tackled semi-supervised video object segmentation by developing the PReMVOS algorithm, which splits the task into proposal generation and merging steps to handle multiple objects across videos, achieving state-of-the-art results with a J & F mean score of 71.6 on DAVIS 2017 test-dev and winning two major challenges.
We address semi-supervised video object segmentation, the task of automatically generating accurate and consistent pixel masks for objects in a video sequence, given the first-frame ground truth annotations. Towards this goal, we present the PReMVOS algorithm (Proposal-generation, Refinement and Merging for Video Object Segmentation). Our method separates this problem into two steps, first generating a set of accurate object segmentation mask proposals for each video frame and then selecting and merging these proposals into accurate and temporally consistent pixel-wise object tracks over a video sequence in a way which is designed to specifically tackle the difficult challenges involved with segmenting multiple objects across a video sequence. Our approach surpasses all previous state-of-the-art results on the DAVIS 2017 video object segmentation benchmark with a J & F mean score of 71.6 on the test-dev dataset, and achieves first place in both the DAVIS 2018 Video Object Segmentation Challenge and the YouTube-VOS 1st Large-scale Video Object Segmentation Challenge.