ICCV 2007 Eleventh IEEE International Conference on Computer Vision Rio de Janeiro, Brazil, October 14-20, 2007 Joint Affinity Propagation for Multiple View Segmentation Jianxiong XIAO, Jingdong WANG, Ping TAN, Long QUAN Department of Computer Science & Engineering The Hong Kong University of Science & Technology
Outline Part 1: Introduction Part 2: Our Approach – Formulation – Optimization: • Hierarchical Sparse Affinity Propagation • Semi-supervised Contraction Part 3: Experiment Results Part 4: Conclusion 2
Outline Part 1: Introduction Part 2: Our Approach – Formulation – Optimization: • Hierarchical Sparse Affinity Propagation • Semi-supervised Contraction Part 3: Experiment Results Part 4: Conclusion 3
Image-based modeling Two Steps Methods: • Get 3D points and camera positions from 2D images (geometry computation) • Get 3D objects from unstructured 3D points (objects reconstruction) input images recovered 3D points recovered object models 4
Structure from motion 5
Data segmentation • Pure 2D segmentation & 3D clustering is hard! – J. Shi and J. Malik. Normalized Cuts and Image Segmentation – etc. • Multiple view joint segmentation – Simultaneously segment 3D points and 2D images – Jointly utilize both 2D and 3D information 2D? 3D? 6
Our work • Explore for multiple view joint segmentation by simultaneously utilizing 2D and 3D data. • The availability of both 2D and 3D data can bring complementary information for segmentation. • Propose two practical algorithms for joint segmentation: – Hierarchical Sparse Affinity Propagation – Semi-supervised Contraction 7
Outline Part 1: Introduction Part 2: Our Approach – Formulation – Optimization: • Hierarchical Sparse Affinity Propagation • Semi-supervised Contraction Part 3: Experiment Results Part 4: Conclusion 8
Outline Part 1: Introduction Part 2: Our Approach – Formulation – Optimization: • Hierarchical Sparse Affinity Propagation • Semi-supervised Contraction Part 3: Experiment Results Part 4: Conclusion 9
Problem formulation The set of images I I i The set of regions I , P u i k k A joint point x , y , z , , P , , n P , x u u 1 1 n L l A set of labels k Set of visibilities V v j Set of joint points X x j We now want to get the inference of L , given X , V and I . 10
Graph based segmentation Graph G = { V , E }: V : 3D points recovered from SFM E : each point connected to its K - nearest neighbors, and two end points of each edge both visible at least in one view graph model 11
Joint similarity s i , j s i , j s i , j 3 c s i , j s i , j ic t • 3D coordinates • 3D normal • Color • Contour • Patch 12
3D similarity 2 p p p p j i i j s i , j 3 d 2 2 3 d n n 2 j i n n i j s i , j 3 n 2 2 3 n s i , j s i , j s i , j 3 3 d 3 n 13
2D color similarity 2 c E E c i j s i , j c 2 2 c med max g t v t i , j v v s i , j v v ic 2 2 ic g = gradient of i-th image i d 2d (p,q) . p . q p q 14
Utilizing the texture information • Hyper Graph? • Higher Order Prior Smoothness? • … 15
Competitive region growing • Associate patches with each 3D point. 16
Patch filtering • A small error around the object boundary may result in a large color difference. 17
Patch histogram similarity For each joint point • Collect all its patches P n • Build an average color histogram h 0 • Down-sample the patches t-1 times • A vector of histograms h h , , h 0 t 1 t 1 1 i j i j s i , j d h , h d h , h t k k t k 0 where d (·, ·) is the dissimilarity measures for histograms. 18
Learning • The concept of segmentation is obviously subjective. • Hence, some user assistant information will greatly improve the segmentation. 19
Handle the ambiguity • To improve robustness and handle the ambiguity of the projections near the boundary 20
Outline Part 1: Introduction Part 2: Our Approach – Formulation – Optimization: • Hierarchical Sparse Affinity Propagation • Semi-supervised Contraction Part 3: Experiment Results Part 4: Conclusion 21
Affinity propagation [Frey & Dueck 2007] • find several exemplars such that the sum of the similarities between the data points and the corresponding exemplars is maximized. • i.e. searching over valid configurations of 1 the labels so as to minimize c , , c c N the energy N E s i , c c i i 1 • i.e. maximizing the net similarity N S E c c c k k 1 22
Responsibility • The responsibility sent from data point r , i k i to candidate exemplar point , reflects the k accumulated evidence for how well-suited k point is to serve as the exemplar for point , i taking into account other potential exemplars for point . i Responsibility i k 23
Availability • The availability , sent from the a , i k i k candidate exemplar point to point , reflects the accumulated evidence for how i appropriate it would be for point to choose k point as its exemplar, taking into account the support from other points that point k should be an exemplar. Availability i k 24
Responsibility & Availability r i , k s i , k max a i , k ' s i , k ' k ' k a i , k min 0 , r k , k max 0 , r i ' , k i ' i , k Responsibility Availability i k 25
Outline Part 1: Introduction Part 2: Our Approach – Formulation – Optimization: • Hierarchical Sparse Affinity Propagation • Semi-supervised Contraction Part 3: Experiment Results Part 4: Conclusion 26
Sparse affinity propagation • Affinity propagation on a sparse graph, called sparse affinity propagation, is more efficient as pointed in [Brendan Frey, Delbert Dueck 2007]. • Then sparse affinity propagation runs in O( T | E |) time with T the number of the iterations and | E | the number of the edges. • Here, the time complexity is O( Tn ) since | E | = O( n ). 27
Original sparse AP • The number of the data points that have the same exemplar i is at most degree( i ), where degree( i ) is the number of nodes connecting i . This will result in unexpectedly too many fragments. 28
Hierarchical sparse AP G ’= G(V,E) ; while (true) { [ Exemplars , Label ] = Sparse Affinity Propagation ( G ’); p , q V ' , p , q E ' , E ' c , c i j Exemplar ( p ) c , Exemplar ( q ) c i j G ’= ( V ’= Exemplars , E’ ); if ( Satisfy Stopping Condition ) break; } 29
Hierarchical sparse AP L=1 L=2 L=5 L=8 L=11 L=14 L=17 30
Outline Part 1: Introduction Part 2: Our Approach – Formulation – Optimization: • Hierarchical Sparse Affinity Propagation • Semi-supervised Contraction Part 3: Experiment Results Part 4: Conclusion 31
Semi-supervised contraction s p , p s q , q 0 32
Semi-supervised contraction 33
Semi-supervised contraction 34
Semi-supervised contraction • Finally, when the algorithm converged, availabilities and responsibilities are combined to identify exemplars. • For point , its corresponding label is i obtained as * k arg max a i , k r i , k k p , q 35
Semi-supervised contraction 36
Outline Part 1: Introduction Part 2: Our Approach – Formulation – Optimization: • Hierarchical Sparse Affinity Propagation • Semi-supervised Contraction Part 3: Experiment Results Part 4: Conclusion 37
Results 38
Results 39
Results 40
Outline Part 1: Introduction Part 2: Our Approach – Formulation – Optimization: • Hierarchical Sparse Affinity Propagation • Semi-supervised Contraction Part 3: Experiment Results Part 4: Conclusion 41
Conclusion 42
ICCV 2007 Eleventh IEEE International Conference on Computer Vision Rio de Janeiro, Brazil, October 14-20, 2007 Joint Affinity Propagation for Multiple View Segmentation Thank you! Questions? Contact: Jianxiong XIAO csxjx@cse.ust.hk 43
2D color similarity • Contour based similarity 44
Recommend
More recommend