Image Segmentation from Shadow-Hints using Minimum Spanning Trees

TL;DR

This paper introduces a new image segmentation method that leverages shadow hints and minimum spanning trees, performing well without training data by using image sequences with static cameras and varying light sources.

Contribution

It presents a novel segmentation approach that does not require training, utilizing shadow cues and minimum spanning trees in specific image sequences.

Findings

Achieves segmentation quality comparable to trained methods

Operates without any training data

Utilizes shadow hints and minimum spanning trees effectively

Abstract

Image segmentation in RGB space is a notoriously difficult task where state-of-the-art methods are trained on thousands or even millions of annotated images. While the performance is impressive, it is still not perfect. We propose a novel image segmentation method, achieving similar segmentation quality but without training. Instead, we require an image sequence with a static camera and a single light source at varying positions, as used in for photometric stereo, for example.