CVDec 26, 2024

When SAM2 Meets Video Shadow and Mirror Detection

arXiv:2412.19293v11 citationsh-index: 1Has Code
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of segmenting rare objects in videos for computer vision researchers, but it is incremental as it applies an existing method to new data.

The study evaluated SAM2 on video shadow and mirror detection tasks, finding its performance suboptimal, particularly with point prompts.

As the successor to the Segment Anything Model (SAM), the Segment Anything Model 2 (SAM2) not only improves performance in image segmentation but also extends its capabilities to video segmentation. However, its effectiveness in segmenting rare objects that seldom appear in videos remains underexplored. In this study, we evaluate SAM2 on three distinct video segmentation tasks: Video Shadow Detection (VSD) and Video Mirror Detection (VMD). Specifically, we use ground truth point or mask prompts to initialize the first frame and then predict corresponding masks for subsequent frames. Experimental results show that SAM2's performance on these tasks is suboptimal, especially when point prompts are used, both quantitatively and qualitatively. Code is available at \url{https://github.com/LeipingJie/SAM2Video}

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes