Yunhai Wang 1 Minglun Gong 1,2 Tianhua Wang 1,3 Hao (Richard) Zhang 4 Daniel Cohen-Or 5 Baoquan Chen 1,6 5 Tel-Aviv University 4 Simon Fraser University.

Slides:



Advertisements
Similar presentations
Yinyin Yuan and Chang-Tsun Li Computer Science Department
Advertisements

SmartBoxes for Interactive Urban Reconstruction Liangliang Nan 1, Andrei Sharf 1, Hao Zhang 2, Daniel Cohen-Or 3, Baoquan Chen 1 1 Shenzhen Institutes.
1/50 Photo-Inspired Model-Driven 3D Object Modeling Kai Xu 1,2 Hanlin Zheng 3 Hao (Richard) Zhang 2 Daniel Cohen-Or 4 Ligang Liu 3 Yueshan Xiong 1 1 National.
Complex Networks for Representation and Characterization of Images For CS790g Project Bingdong Li 9/23/2009.
Efficient High-Resolution Stereo Matching using Local Plane Sweeps Sudipta N. Sinha, Daniel Scharstein, Richard CVPR 2014 Yongho Shin.
L1 sparse reconstruction of sharp point set surfaces
Foreground Focus: Finding Meaningful Features in Unlabeled Images Yong Jae Lee and Kristen Grauman University of Texas at Austin.
Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
Hongliang Li, Senior Member, IEEE, Linfeng Xu, Member, IEEE, and Guanghui Liu Face Hallucination via Similarity Constraints.
1 Enviromatics Spatial database systems Spatial database systems Вонр. проф. д-р Александар Маркоски Технички факултет – Битола 2008 год.
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
Graph-Based Image Segmentation
Texture Segmentation Based on Voting of Blocks, Bayesian Flooding and Region Merging C. Panagiotakis (1), I. Grinias (2) and G. Tziritas (3)
Structure Recovery by Part Assembly Chao-Hui Shen 1 Hongbo Fu 2 Kang Chen 1 Shi-Min Hu 1 1 Tsinghua University 2 City University of Hong Kong.
Shape from Contours and Multiple Stereo A Hierarchical, Mesh-Based Approach Hendrik Kück, Wolfgang Heidrich, Christian Vogelgsang.
Silhouettes in Multiview Stereo Ian Simon. Multiview Stereo Problem Input: – a collection of images of a rigid object (or scene) – camera parameters for.
Event prediction CS 590v. Applications Video search Surveillance – Detecting suspicious activities – Illegally parked cars – Abandoned bags Intelligent.
Boundary matting for view synthesis Samuel W. Hasinoff Sing Bing Kang Richard Szeliski Computer Vision and Image Understanding 103 (2006) 22–32.
Small Codes and Large Image Databases for Recognition CVPR 2008 Antonio Torralba, MIT Rob Fergus, NYU Yair Weiss, Hebrew University.
Surface Reconstruction from 3D Volume Data. Problem Definition Construct polyhedral surfaces from regularly-sampled 3D digital volumes.
A Study of Approaches for Object Recognition
Human Posture Recognition with Convex Programming Hao Jiang, Ze-Nian Li and Mark S. Drew School of Computing Science Simon Fraser University Burnaby, BC,
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Prior Knowledge for Part Correspondence Oliver van Kaick 1, Andrea Tagliasacchi 1, Oana Sidi 2, Hao Zhang 1, Daniel Cohen-Or 2, Lior Wolf 2, Ghassan Hamarneh.
Johannes Kopf Billy Chen Richard Szeliski Michael Cohen Microsoft Research Microsoft Microsoft Research Microsoft Research.
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Autonomous Learning of Object Models on Mobile Robots Xiang Li Ph.D. student supervised by Dr. Mohan Sridharan Stochastic Estimation and Autonomous Robotics.
Thien Anh Dinh1, Tomi Silander1, Bolan Su1, Tianxia Gong
Problem Statement A pair of images or videos in which one is close to the exact duplicate of the other, but different in conditions related to capture,
CS654: Digital Image Analysis Lecture 3: Data Structure for Image Analysis.
1 Style-Content Separation by Anisotropic Part Scales Kai Xu, Honghua Li, Hao Zhang, Daniel Cohen-Or Yueshan Xiong, Zhi-Quan Cheng Simon Fraser Universtiy.
Interactive Discovery and Semantic Labeling of Patterns in Spatial Data Thomas Funkhouser, Adam Finkelstein, David Blei, and Christiane Fellbaum Princeton.
ALIGNMENT OF 3D ARTICULATE SHAPES. Articulated registration Input: Two or more 3d point clouds (possibly with connectivity information) of an articulated.
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
Intelligent Vision Systems ENT 496 Object Shape Identification and Representation Hema C.R. Lecture 7.
Organizing Heterogeneous Scene Collections through Contextual Focal Points Kai Xu, Rui Ma, Hao Zhang, Chenyang Zhu, Ariel Shamir, Daniel Cohen-Or, Hui.
#MOTION ESTIMATION AND OCCLUSION DETECTION #BLURRED VIDEO WITH LAYERS
Experiments Test different parking lot images captured in different luminance conditions The test samples include 1300 available parking spaces and 1500.
Stereo Many slides adapted from Steve Seitz.
IEEE Int'l Symposium on Signal Processing and its Applications 1 An Unsupervised Learning Approach to Content-Based Image Retrieval Yixin Chen & James.
Ground Truth Free Evaluation of Segment Based Maps Rolf Lakaemper Temple University, Philadelphia,PA,USA.
PSEUDO-RELEVANCE FEEDBACK FOR MULTIMEDIA RETRIEVAL Seo Seok Jun.
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Scene Completion Using Millions of Photographs James Hays, Alexei A. Efros Carnegie Mellon University ACM SIGGRAPH 2007.
Geodesic Saliency Using Background Priors
By Pushpita Biswas Under the guidance of Prof. S.Mukhopadhyay and Prof. P.K.Biswas.
Similarity Measures Spring 2009 Ben-Gurion University of the Negev.
Implicit Active Shape Models for 3D Segmentation in MR Imaging M. Rousson 1, N. Paragio s 2, R. Deriche 1 1 Odyssée Lab., INRIA Sophia Antipolis, France.
A Part-aware Surface Metric for Shape Analysis Rong Liu 1, Hao Zhang 1, Ariel Shamir 2, and Daniel Cohen-Or 3 1 Simon Fraser University, Canada 2 The Interdisciplinary.
CSC321 Lecture 24 Using Boltzmann machines to initialize backpropagation Geoffrey Hinton.
CSC321 Lecture 27 Using Boltzmann machines to initialize backpropagation Geoffrey Hinton.
Energy minimization Another global approach to improve quality of correspondences Assumption: disparities vary (mostly) smoothly Minimize energy function:
Correspondence and Stereopsis. Introduction Disparity – Informally: difference between two pictures – Allows us to gain a strong sense of depth Stereopsis.
Student: Shunan Shi Professor: Hao Zhang CMPT888.
Technological Uncanny K. S'hell, C Kurtz, N. Vincent et E. André et M. Beugnet 1.
Prior Knowledge for Part Correspondence
Table 1. Advantages and Disadvantages of Traditional DM/ML Methods
Nonparametric Semantic Segmentation
You can check broken videos in this slide here :
Saliency detection Donghun Yeo CV Lab..
Mean Shift Segmentation
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
A New Approach to Track Multiple Vehicles With the Combination of Robust Detection and Two Classifiers Weidong Min , Mengdan Fan, Xiaoguang Guo, and Qing.
Image Segmentation Techniques
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Lecture 31: Graph-Based Image Segmentation
Fourier Transform of Boundaries
“Traditional” image segmentation
Learning complex visual concepts
SmartBoxes for Interactive Urban Reconstruction
Presentation transcript:

Yunhai Wang 1 Minglun Gong 1,2 Tianhua Wang 1,3 Hao (Richard) Zhang 4 Daniel Cohen-Or 5 Baoquan Chen 1,6 5 Tel-Aviv University 4 Simon Fraser University 1 Shenzhen Institutes of Advanced Technology 6 Shandong University 3 Jilin University 2 Memorial University of Newfoundland

2/40  One of the most fundamental tasks in shape analysis  Low-level cues (minimal rule; convexity) alone insufficient

3/40 3 Learning segmentation [Kalograkis et al. 10] Active co-analysis [Wang et al. 2012] Unsupervised co-analysis [Sidi et al. 2011] Joint segmentation [Huang et al. 2011] Keys to success: amount & quality of labelled or unlabelled 3D data

4/ labeled meshes over 19 object categories  How many 3D models of strollers, golf carts, gazebos, …?  Not enough 3D models = insufficient knowledge  Labeling 3D shapes is also a non-trivial task

5/40 About 14 million images across almost 22,000 object categories Labeling images is quite a bit easier than labeling 3D shapes

6/40 6 Incomplete Real-world 3D models (e.g., those from Tremble Warehouse) are often imperfect Self-intersecting; non-manifold

7/40 Treat a 3D shape as a set of projected binary images  Alleviate various data artifacts in 3D, e.g., self- intersections  Then propagate the image labels to the 3D shape  Label these images by learning from vast amount of image data

8/40 Joint image-shape analysis via projective analysis for semantic 3D segmentation  Utilize vast amount of available image data  Allowing us to analyze imperfect 3D shapes

9/40 Bi-class Symmetric Hausdorff distance = BiSH  Designed for matching 1D binary images  More sensitive to topology changes (holes)  Caters to our needs: part-aware label transfer

10/40 10 Image-guided 3D modeling [Xu et al.11] Many works on 2D-3D fusion, e.g., for reconstruction [Li et al.11]

11/40 11 Light field descriptor for 3D shape retrieval [Chen et al.03] Image-space simplification error [Lindstrom and Turk 10] We deal with the higher-level and more delicate task of semantic 3D segmentation

12/40 PSA for 3D shape segmentation Region-based binary shape matching Results and conclusion

13/40 Labeling involves GrabCut and some user assistance

14/40 Assume all objects are upright oriented; they mostly are! Project an input 3D shape from multiple pre-set viewpoints

15/40 For each projection of the input 3D shape, retrieve top matches from the set of labelled images

16/40 Select top (non-adjacent) projections with the smallest average matching costs for label transfer

17/40 Label transfer is done per corresponding horizontal slabs Pixel correspondence straightforward Later …

18/40 Label transfer is weighted by a confidence value per pixel  Three terms based on image-level, slab-level, and pixel-level similarity: more similar = higher confidence

19/40 Probabilistic map over input 3D shape: computed by integrating per-pixel confidence values over each shape primitive  One primitive projects to multiple pixels in multiple images  Per-pixel confidence gathered over multiple retrieved images

20/40 Final labeling of 3D shape: multi-label alpha expansion graph cuts based on the probabilistic map

21/40 PSA for 3D shape segmentation Region-based binary shape matching Results and conclusion

22/40 Projections of input 3D shape … Database of (labeled) images … Characteristics of the data to be matched  Possibly complex topology (lots of holes), not just a contour  All upright orientated: to be exploited Goal: find shapes most suitable for label transfer and FAST!  Not a global visual similarity based retrieval  Want part-aware label transfer but cannot reliably segment Classical descriptors, e.g., shape context, interior distance shape context (IDSC), GIST, Zenike moments, Fourier descriptors, etc., do not quite fulfill our needs

23/40 Takes advantage of upright orientation

24/40 Classical choice for distance: symmetric Hausdorff (SH) But not sensitive to topology changes; not part-aware Cluster scan-lines into smaller number of slabs --- efficiency! Hierarchical clustering by a distance between adjacent slabs

25/40 SH for only one class may not be topology- sensitive A bi-class SH distance is! A B C B SH(A,B)=2, SH(A c, B c )=10 SH(C,B)=2, SH(C c, B c )=2

26/40 A B C B SH(A,B)=2, SH(A c, B c )=10 SH(C,B)=2, SH(C c, B c )=2 BiSH(C,B) = 2 BiSH(A,B) = 10

27/40 BiSH SH BiSH is more part-aware: new slabs near part boundaries

28/40 Slabs are scaled/warped vertically for better alignment Another measure to encourage part-aware label transfer Slabs of labeled image warped to better align with slabs in projected image Warp Slabs recolored: many-to-one slab matching possible Recolor

29/40 Dissimilarity between slabs: BiSH scaled by slab height Slab matching allows linear warp: optimized by a dynamic time warping (DTW) algorithm Dissimilarity between images: sum over slab dissimilarity after warped slab matching

30/40 PSA for 3D shape segmentation Region-based binary shape matching Results and conclusion

31/40 Same inputs, training data (we project), and experimental setting Models in [K 2010]: manifold, complete, no self- intersections PSA allows us to handle any category and imperfect shapes

32/40 11 object categories; about 2600 labeled images All input 3D shapes tested have self-intersections as well as other data artifacts

33/40 Pavilion (465 pieces) Bicycle (704 pieces)

34/40

35/40 Matching two images (512 x 512) takes 0.06 seconds Label transfer (2D-to-2D then to 3D): about 1 minute for a 20K-triangle mesh  Number of selected projections: 5 – 10  Number of retrieved images per projection: 2

36/40 Projective shape analysis (PSA): semantic 3D segmentation by learning from labeled 2D images 36 Demonstrated potential in labeling 3D models: imperfect, complex topology, over any category

37/40 No strong requirements on quality of 3D model Utilize the rich availability and ease of processing of photos for 3D shape analysis

38/40 Inherent limitation of 2D projections: they do not fully capture 3D info Inherent to data-driven: knowledge has to be in data Assuming upright; not designed for articulated shapes Relying on spatial and not feature-space analysis

39/40 Labeling 2D images is still tedious: unsupervised projective analysis Additional cues from images and projections, e.g., color, depth, etc. Apply PSA for other knowledge-driven analyses

40/40 40 More results and data can be found from