Image Segmentation from Shadow-Hints using Minimum Spanning Trees
This addresses the challenge of image segmentation for applications where training data is limited or unavailable, though it is incremental as it builds on photometric stereo techniques.
The paper tackles the problem of image segmentation in RGB space by proposing a novel method that achieves similar segmentation quality to state-of-the-art trained methods, but without requiring training, instead using an image sequence with a static camera and varying light source positions.
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.