1 / 13

How to and how not to use graph cuts

How to and how not to use graph cuts. Karen Liu and Brett Allen. You want to minimize:. What graph cuts is good for. Suppose you want to label the nodes in a graph:. For each node, you have: a data term: D ( p , f p ) – the cost of labeling node p with label f p

Download Presentation

How to and how not to use graph cuts

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. How to and how not to usegraph cuts Karen Liu and Brett Allen

  2. You want to minimize: What graph cuts is good for • Suppose you want to label the nodes in a graph: • For each node, you have: • a data term: D(p, fp) – the cost of labeling node p with label fp • a neighbor term, V(fp, fq), the cost of labeling connected nodes p and q with labels fp and fq.

  3. The algorithm • we used an existing min-cut implementation • for each α-expansion, we build a graph that expresses the desirability of switching each node’s label to α ( ):

  4. Application 1: Stripe labeling A harder case

  5. Using graph cuts

  6. Results

  7. What went wrong?! True labeling: … 11 12 13 14 15 16 17 18 19 … Current labeling: … 11 12 13 1 2 3 17 18 19 … …any α-expansion will not improve the energy! α-expansion only works if:

  8. Application 2: Stereo

  9. Using graph cuts

  10. Results Ground truth Graph cuts Parameters: 12 labels (12-34 pixel displacement), w = 10

  11. Results

  12. Results (2) Input Ground truth Graph cuts

  13. Results (3)

More Related