Coarse-to-Fine Segmentation With Shape-Tailored Scale Spaces
This work addresses motion segmentation by reducing sensitivity to fine-scale noise, though it is incremental as it builds on existing scale-space and energy-based segmentation approaches.
The paper tackles the problem of segmenting coarse structures without smoothing across region boundaries by formulating a multi-scale energy and method, and demonstrates improved performance on motion segmentation benchmarks with reduced sensitivity to fine-scale clutter.
We formulate a general energy and method for segmentation that is designed to have preference for segmenting the coarse structure over the fine structure of the data, without smoothing across boundaries of regions. The energy is formulated by considering data terms at a continuum of scales from the scale space computed from the Heat Equation within regions, and integrating these terms over all time. We show that the energy may be approximately optimized without solving for the entire scale space, but rather solving time-independent linear equations at the native scale of the image, making the method computationally feasible. We provide a multi-region scheme, and apply our method to motion segmentation. Experiments on a benchmark dataset shows that our method is less sensitive to clutter or other undesirable fine-scale structure, and leads to better performance in motion segmentation.