1 / 30

Learning Decompositional Shape Models from Examples

This study aims to automatically construct a generic hierarchical shape model from exemplars. The challenges include dealing with different appearances, ambiguous features, and lack of one-to-one correspondence. The proposed approach involves layered motion segmentations, categorical features matching, and many-to-many graph matching.

gjohn
Download Presentation

Learning Decompositional Shape Models from Examples

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. Learning Decompositional Shape Models from Examples Alex Levinshtein Cristian Sminchisescu Sven Dickinson University of Toronto

  2. Hierarchical Models Manually built hierarchical model proposed by Marr And Nishihara (“Representation and recognition of the spatial organization of three dimensional shapes”, Proc. of Royal Soc. of London, 1978)

  3. Our goal Automatically construct a generic hierarchical shape model from exemplars • Challenges: • Cannot assume similar appearance among different exemplars • Generic features are highly ambiguous • Generic features may not be in one-to-one correspondence

  4. Layered Motion SegmentationsKumar, Torr and Zisserman, ICCV 2005 • Models image projection, lighting and motion blur • Models spatial continuity, occlusions, and works over multiple frames (cf. earlier work by Jojic & Frey, CVPR 2001) • Estimates the number of segments, their mattes, layer assignment, appearance, lighting and transformation parameters for each segment • Initialization using loopy BP, refinement using graph cuts

  5. Constellation models Fergus, R., Perona, P., and Zisserman, A., “Object Class Recognition by Unsupervised Scale-Invariant Learning”, CVPR 2003

  6. Categorical features Match

  7. Automatically constructed Hierarchical Models Input: Question: What is it? Output:

  8. Stages of the system Exemplar images Extract Blob Graphs Blob graphs Match Blob Graphs (many-to-many) Many-to-many correspondences Extract Parts Extract Decomposition Relations Extract Attachment Relations Model parts Model decomposition relations Model attachment relations Assemble Final Model

  9. Blob Graph Construction Exemplar images Extract Blob Graphs Blob graphs Match Blob Graphs (many-to-many) Many-to-many correspondences Extract Parts Extract Decomposition Relations Extract Attachment Relations Model parts Model decomposition relations Model attachment relations Assemble Final Model

  10. Blob Graph Construction • On the Representation and Matching of Qualitative Shape at Multiple Scales • A. Shokoufandeh, S. Dickinson, C. Jonsson, L. Bretzner, and T. Lindeberg,ECCV 2002 • Edges are invariant to articulation • Choose the largest connected component.

  11. Blob Graph Construction Perceptual grouping of blobs: Connectivity measure: max{d1/major(A), d2/major(B)}

  12. Feature matching Exemplar images Extract Blob Graphs Blob graphs Match Blob Graphs (many-to-many) Many-to-many correspondences Extract Parts Extract Decomposition Relations Extract Attachment Relations Model parts Model decomposition relations Model attachment relations Assemble Final Model

  13. Feature matching One-to-one matching. Rely on shape and context, not appearance! Many-to-many matching

  14. A Many-to-Many Graph Matching Framework 1. Embed graphs with low distortion to yield weighted point distributions. 2. Compute many-to-many correspondences between the two distributions using EMD. 3. The computed flows yield a many-to-many node correspondence between the two graphs. Demirci, Shokoufandeh, Dickinson, Keselman, and Bretzner (ECCV 2004)

  15. Feature embedding and EMD Spectral embedding

  16. Returning to our set of inputs • Many-to-many matching of every pair of exemplars.

  17. Part Extraction Exemplar images Extract Blob Graphs Blob graphs Match Blob Graphs (many-to-many) Many-to-many correspondences Extract Parts Extract Decomposition Relations Extract Attachment Relations Model parts Model decomposition relations Model attachment relations Assemble Final Model

  18. Many-to-many matching results

  19. Results of the part extraction stage

  20. Extracting attachment relations Exemplar images Extract Blob Graphs Blob graphs Match Blob Graphs (many-to-many) Many-to-many correspondences Extract Parts Extract Decomposition Relations Extract Attachment Relations Model parts Model decomposition relations Model attachment relations Assemble Final Model

  21. Extracting attachment relations Number of times blobs drawn from the two clusters were attached is high Right arm is typically connected to torso in exemplar images ! Number of times blobs from the two clusters co-appeared in an image. Torso Right Arm

  22. Extracting decomposition relations Exemplar images Extract Blob Graphs Blob graphs Match Blob Graphs (many-to-many) Many-to-many correspondences Extract Parts Extract Decomposition Relations Extract Attachment Relations Model parts Model decomposition relations Model attachment relations Assemble Final Model

  23. Extracting decomposition relations Left Arm Upper Lower

  24. Assemble Final Model Exemplar images Extract Blob Graphs Blob graphs Match Blob Graphs (many-to-many) Many-to-many correspondences Extract Parts Extract Decomposition Relations Extract Attachment Relations Model parts Model decomposition relations Model attachment relations Assemble Final Model

  25. Results

  26. Conclusions • Generic models must be defined at multiple levels of abstraction, as Marr proposed. • Coarse shape features, such as blobs, are highly ambiguous and cannot be matched without contextual constraints. • Moreover, features that exist at different levels of abstraction must be matched many-to-many in the presence of noise. • The many-to-many matching results can be analyzed to yield both the parts and relations of a decompositional model. • Preliminary results indicate that a limited decompositional model can be learned from a set of noisy examples.

  27. Future work • Construct models for objects other than humans – objects with richer decompositional hierarchies. • Automatically learn perceptual grouping relations between blobs from labeled examples. • Develop indexing and matching frameworks for decompositional models.

More Related