Superpixel lattices

TLDR

Unsupervised over‑segmentation into superpixels is a common preprocessing step, but existing methods lose the regular grid topology, so superpixels lack consistent positions or neighbor relationships. The authors propose a novel algorithm that forces superpixels to conform to a regular grid lattice. The algorithm generates grid‑conforming superpixels and is evaluated using image reconstruction, comparison to human‑segmented images, and stability across video frames. Despite the added topological constraint, the algorithm matches alternative segmentation methods in speed and accuracy.

Abstract

Unsupervised over-segmentation of an image into superpixels is a common preprocessing step for image parsing algorithms. Ideally, every pixel within each superpixel region will belong to the same real-world object. Existing algorithms generate superpixels that forfeit many useful properties of the regular topology of the original pixels: for example, the nth superpixel has no consistent position or relationship with its neighbors. We propose a novel algorithm that produces superpixels that are forced to conform to a grid (a regular superpixel lattice). Despite this added topological constraint, our algorithm is comparable in terms of speed and accuracy to alternative segmentation approaches. To demonstrate this, we use evaluation metrics based on (i) image reconstruction (ii) comparison to human-segmented images and (iii) stability of segmentation over subsequent frames of video sequences.