Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps
This work addresses the need for efficient and precise video object segmentation for users in fields like video editing and computer vision, though it appears incremental as it builds on existing interactive methods.
The paper tackles the problem of interactive video object segmentation by proposing a guided interactive segmentation algorithm that improves accuracy and reduces user interaction time, achieving faster and more accurate results than conventional methods.
We propose a novel guided interactive segmentation (GIS) algorithm for video objects to improve the segmentation accuracy and reduce the interaction time. First, we design the reliability-based attention module to analyze the reliability of multiple annotated frames. Second, we develop the intersection-aware propagation module to propagate segmentation results to neighboring frames. Third, we introduce the GIS mechanism for a user to select unsatisfactory frames quickly with less effort. Experimental results demonstrate that the proposed algorithm provides more accurate segmentation results at a faster speed than conventional algorithms. Codes are available at https://github.com/yuk6heo/GIS-RAmap.