The Princeton Shape Benchmark Philip Shilane, Patrick Min, Michael Kazhdan, and Thomas Funkhouser.

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

Shape Analysis and Retrieval D2 Shape Distributions Notes courtesy of Funk et al., SIGGRAPH 2004.
Aggregating local image descriptors into compact codes
Wavelets Fast Multiresolution Image Querying Jacobs et.al. SIGGRAPH95.
Three things everyone should know to improve object retrieval
Presented by Xinyu Chang
Evaluating Color Descriptors for Object and Scene Recognition Koen E.A. van de Sande, Student Member, IEEE, Theo Gevers, Member, IEEE, and Cees G.M. Snoek,
Evaluating Sketch Query Interfaces for a 3D Model Search Engine Patrick Min Joyce Chen, Tom Funkhouser Princeton Workshop on Shape-Based Retrieval and.
1 CS 391L: Machine Learning: Instance Based Learning Raymond J. Mooney University of Texas at Austin.
A NOVEL LOCAL FEATURE DESCRIPTOR FOR IMAGE MATCHING Heng Yang, Qing Wang ICME 2008.
Mesh modeling and processing M. Ramanathan STTP CAD 2011Mesh modeling and processing.
3D Shape Histograms for Similarity Search and Classification in Spatial Databases. Mihael Ankerst,Gabi Kastenmuller, Hans-Peter-Kriegel,Thomas Seidl Univ.
Yuanlu Xu Human Re-identification: A Survey.
Software Quality Ranking: Bringing Order to Software Modules in Testing Fei Xing Michael R. Lyu Ping Guo.
Shape Analysis and Retrieval ( ) (Michael) Misha Kazhdan.
Computer Vision Group, University of BonnVision Laboratory, Stanford University Abstract This paper empirically compares nine image dissimilarity measures.
Group 3 Akash Agrawal and Atanu Roy 1 Raster Database.
Shape-Based Retrieval of Articulated 3D Models Using Spectral Embedding GrUVi Lab, School of Computing Science Simon Fraser University, Burnaby, BC Canada.
Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors Michael Kazhdan Thomas Funkhouser Szymon Rusinkiewicz Princeton University.
Robert Osada, Tom Funkhouser Bernard Chazelle, and David Dobkin Princeton University Matching 3D Models With Shape Distributions.
Reflective Symmetry Detection in 3 Dimensions
2006 3D Shape Retrieval Contest Remco Veltkamp, Utrecht University.
Retrieval Evaluation: Precision and Recall. Introduction Evaluation of implementations in computer science often is in terms of time and space complexity.
Harmonic 3D Shape Matching Michael Kazhdan Thomas Funkhouser Princeton University Michael Kazhdan Thomas Funkhouser Princeton University.
1 Zafer BarutcuogluPrinceton University Christopher DeCoro Hierarchical Shape Classification Using Bayesian Aggregation.
Selecting Distinctive 3D Shape Descriptors for Similarity Retrieval Philip Shilane and Thomas Funkhouser.
Shape Descriptors I Thomas Funkhouser CS597D, Fall 2003 Princeton University Thomas Funkhouser CS597D, Fall 2003 Princeton University.
Shape Matching and Anisotropy Michael Kazhdan, Thomas Funkhouser, and Szymon Rusinkiewicz Princeton University Michael Kazhdan, Thomas Funkhouser, and.
Retrieval Evaluation. Introduction Evaluation of implementations in computer science often is in terms of time and space complexity. With large document.
Using Relevance Feedback in Multimedia Databases
Gait Recognition Simon Smith Jamie Hutton Thomas Moore David Newman.
1 Invariant Local Feature for Object Recognition Presented by Wyman 2/05/2006.
Chapter 5: Information Retrieval and Web Search
CAD’11, TaipeiDepartment of Engineering Design, IIT Madras M. Ramanathan Department of Engineering Design Indian Institute of Technology Madras.
Improving web image search results using query-relative classifiers Josip Krapacy Moray Allanyy Jakob Verbeeky Fr´ed´eric Jurieyy.
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
AdvisorStudent Dr. Jia Li Shaojun Liu Dept. of Computer Science and Engineering, Oakland University 3D Shape Classification Using Conformal Mapping In.
Alignment Introduction Notes courtesy of Funk et al., SIGGRAPH 2004.
3D Sketch-based 3D Model Retrieval With Kinect Natacha Feola 1, Azeem Ghumman 2, Scott Forster 3, Dr. Yijuan Lu 4 1 Department of Computer Science, University.
Shape Matching for Model Alignment 3D Scan Matching and Registration, Part I ICCV 2005 Short Course Michael Kazhdan Johns Hopkins University.
Alignment and Matching
Recognition using Regions (Demo) Sudheendra V. Outline Generating multiple segmentations –Normalized cuts [Ren & Malik (2003)] Uniform regions –Watershed.
Signal Processing and Representation Theory Lecture 4.
Video Google: A Text Retrieval Approach to Object Matching in Videos Josef Sivic and Andrew Zisserman.
Chapter 6: Information Retrieval and Web Search
1 Multiple Classifier Based on Fuzzy C-Means for a Flower Image Retrieval Keita Fukuda, Tetsuya Takiguchi, Yasuo Ariki Graduate School of Engineering,
Shape Descriptors Thomas Funkhouser and Michael Kazhdan Princeton University Thomas Funkhouser and Michael Kazhdan Princeton University.
IEEE Int'l Symposium on Signal Processing and its Applications 1 An Unsupervised Learning Approach to Content-Based Image Retrieval Yixin Chen & James.
References: [1]S.M. Smith et al. (2004) Advances in functional and structural MR image analysis and implementation in FSL. Neuroimage 23: [2]S.M.
A Statistical Method for 3D Object Detection Applied to Face and Cars CVPR 2000 Henry Schneiderman and Takeo Kanade Robotics Institute, Carnegie Mellon.
Shape Analysis and Retrieval
Visual Categorization With Bags of Keypoints Original Authors: G. Csurka, C.R. Dance, L. Fan, J. Willamowski, C. Bray ECCV Workshop on Statistical Learning.
Ivica Dimitrovski 1, Dragi Kocev 2, Suzana Loskovska 1, Sašo Džeroski 2 1 Faculty of Electrical Engineering and Information Technologies, Department of.
Data Mining, ICDM '08. Eighth IEEE International Conference on Duy-Dinh Le National Institute of Informatics Hitotsubashi, Chiyoda-ku Tokyo,
2004/03/03Sheun-Huei Guan, CML, NTU1 3D Model Retrieval After Shape Distributions.
Introduction to Data Mining by Yen-Hsien Lee Department of Information Management College of Management National Sun Yat-Sen University March 4, 2003.
Partial Shape Matching. Outline: Motivation Sum of Squared Distances.
Skeleton Extraction of 3D Objects by Radial Basis Functions for Content-based Retrieval in MPEG-7 Ming Ouhyoung Fu-Che Wu, Wan-Chun Ma, Communication and.
Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz, Antonio Torralba Massachusetts Institute of Technology
Predicting User Interests from Contextual Information R. W. White, P. Bailey, L. Chen Microsoft (SIGIR 2009) Presenter : Jae-won Lee.
Similarity Measurement and Detection of Video Sequences Chu-Hong HOI Supervisor: Prof. Michael R. LYU Marker: Prof. Yiu Sang MOON 25 April, 2003 Dept.
Applied Cartography and Introduction to GIS GEOG 2017 EL Lecture-5 Chapters 9 and 10.
What Is Cluster Analysis?
Evaluating Techniques for Image Classification
PRESENTED BY Yang Jiao Timo Ahonen, Matti Pietikainen
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
Zan Gao, Deyu Wang, Xiangnan He, Hua Zhang
Shape Analysis and Retrieval
The Open World of Micro-Videos
Improving Retrieval Performance of Zernike Moment Descriptor on Affined Shapes Dengsheng Zhang, Guojun Lu Gippsland School of Comp. & Info Tech Monash.
Presentation transcript:

The Princeton Shape Benchmark Philip Shilane, Patrick Min, Michael Kazhdan, and Thomas Funkhouser

Shape Retrieval Problem 3D ModelShape Descriptor Model Database Best Matches

Example Shape Descriptors D2 Shape Distributions Extended Gaussian Image Shape Histograms Spherical Extent Function Spherical Harmonic Descriptor Light Field Descriptor etc.

Example Shape Descriptors D2 Shape Distributions Extended Gaussian Image Shape Histograms Spherical Extent Function Spherical Harmonic Descriptor Light Field Descriptor etc. How do we know which is best?

Typical Retrieval Experiment Create a database of 3D models Group the models into classes For each model: Rank other models by similarity Measure how many models in the same class appear near the top of the ranked list Present average results

Typical Retrieval Experiment Create a database of 3D models Group the models into classes For each model: Rank other models by similarity Measure how many models in the same class appear near the top of the ranked list Present average results

Typical Retrieval Experiment Create a database of 3D models Group the models into classes For each model: Rank other models by similarity Measure how many models in the same class appear near the top of the ranked list Present average results

Typical Retrieval Experiment Create a database of 3D models Group the models into classes For each model: Rank other models by similarity Measure how many models in the same class appear near the top of the ranked list Present average results Query

Typical Retrieval Experiment Query Create a database of 3D models Group the models into classes For each model: Rank other models by similarity Measure how many models in the same class appear near the top of the ranked list Present average results

Typical Retrieval Experiment Query Create a database of 3D models Group the models into classes For each model: Rank other models by similarity Measure how many models in the same class appear near the top of the ranked list Present average results

Typical Retrieval Experiment Create a database of 3D models Group the models into classes For each model: Rank other models by similarity Measure how many models in the same class appear near the top of the ranked list Present average results

Typical Retrieval Experiment Create a database of 3D models Group the models into classes For each model: Rank other models by similarity Measure how many models in the same class appear near the top of the ranked list Present average results

Shape Retrieval Results Shape Descriptor Compare Time (µs) Storage Size (bytes) Norm. DCGain LFD1,3004, % REXT22917, % SHD272, % GEDT45032, % EXT % SECSHEL45132, % VOXEL45032, % SECTORS % CEGI272, % EGI141, % D % SHELLS %

Outline Introduction Related work Princeton Shape Benchmark Comparison of 12 descriptors Evaluation techniques Results Conclusion

Typical Shape Databases Num Models Num Classes Num Classified Largest Class Osada % MPEG-71, % Hilaga % Technion1, % Zaharia1, % CCCC1, % Utrecht % Taiwan1, % Viewpoint1,890851,28012%

Typical Shape Databases Num Models Num Classes Num Classified Largest Class Osada % MPEG-71, % Hilaga % Technion1, % Zaharia1, % CCCC1, % Utrecht % Taiwan1, % Viewpoint1,890851,28012%

Typical Shape Databases Num Models Num Classes Num Classified Largest Class Osada % MPEG-71, % Hilaga % Technion1, % Zaharia1, % CCCC1, % Utrecht % Taiwan1, % Viewpoint1,890851,28012% Aerodynamic

Typical Shape Databases Num Models Num Classes Num Classified Largest Class Osada % MPEG-71, % Hilaga % Technion1, % Zaharia1, % CCCC1, % Utrecht % Taiwan1, % Viewpoint1,890851,28012% Letter ‘C’

Typical Shape Databases

153 dining chairs25 living room chairs16 beds12 dining tables 8 chests28 bottles39 vases 36 end tables Typical Shape Databases

Goal: Benchmark for 3D Shape Retrieval Large number of classified models Wide variety of class types Not too many or too few models in each class Standardized evaluation tools Ability to investigate properties of descriptors Freely available to researchers

Princeton Shape Benchmark Large shape database 6,670 models 1,814 classified models, 161 classes Separate training and test sets Standardized suite of tests Multiple classifications Targeted sets of queries Standardized evaluation tools Visualization software Quantitative metrics

Princeton Shape Benchmark 51 potted plants33 faces15 desk chairs22 dining chairs 100 humans28 biplanes14 flying birds11 ships

Num Models Num Classes Num Classified Largest Class Osada % MPEG-71, % Hilaga % Technion1, % Zaharia1, % CCCC1, % Utrecht % Taiwan1, % Viewpoint1,890851,28012% PSB6, ,8146% Princeton Shape Benchmark (PSB)

Outline Introduction Related work Princeton Shape Benchmark Comparison of 12 descriptors Evaluation techniques Results Conclusion

Comparison of Shape Descriptors Shape Histograms (Shells) Shape Histograms (Sectors) Shape Histograms (SecShells) D2 Shape Distributions Extended Gaussian Image (EGI) Complex Extended Gaussian Image (CEGI) Spherical Extent Function (EXT) Radialized Spherical Extent Function (REXT) Voxel Gaussian Euclidean Distance Transform (GEDT) Spherical Harmonic Descriptor (SHD) Light Field Descriptor (LFD)

Comparison of Shape Descriptors

Evaluation Tools Visualization tools Precision/recall plot Best matches Distance image Tier image Quantitative metrics Nearest neighbor First and Second tier E-Measure Discounted Cumulative Gain (DCG)

Evaluation Tools Visualization tools Precision/recall plot Best matches Distance image Tier image Quantitative metrics Nearest neighbor First and Second tier E-Measure Discounted Cumulative Gain (DCG)

Evaluation Tools Visualization tools Precision/recall plot Best matches Distance image Tier image Quantitative metrics Nearest neighbor First and Second tier E-Measure Discounted Cumulative Gain (DCG) QueryCorrect class Wrong class

Evaluation Tools Visualization tools Precision/recall plot Best matches Distance image Tier image Quantitative metrics Nearest neighbor First and Second tier E-Measure Discounted Cumulative Gain (DCG)

Evaluation Tools Visualization tools Precision/recall plot Best matches Distance image Tier image Quantitative metrics Nearest neighbor First and Second tier E-Measure Discounted Cumulative Gain (DCG)

Dining Chair Desk Chair Evaluation Tools Visualization tools Precision/recall plot Best matches Distance image Tier image Quantitative metrics Nearest neighbor First and Second tier E-Measure Discounted Cumulative Gain (DCG)

Function vs. Shape Functional at the top levels of the hierarchy, shape based at the lower levels Rectangular table Round table Furniture Table Man-made Natural root Vehicle Chair

Base Classification (92 classes) Man-made Furniture Table Round table

Coarse Classification (44 classes) Man-made Furniture Table Round table

Coarser Classification (6 classes) Man-made Furniture Table Round table

Coarsest Classification (2 classes) Man-made Furniture Table Round table

Granularity Comparison Base (92) Man-made vs. Natural (2)

Rotationally Aligned Models (650)

All Models (907)

Complex Models (200)

Performance by Property Rotation Aligned Base Depth Complexity LFD REXT SHD GEDT EXT SecShells Voxel Sectors CEGI EGI D Shells

Methodology to compare shape descriptors Vary classifications Query lists targeted at specific properties Unexpected results EGI: good at discriminating man-made vs. natural objects, though poor at fine-grained distinctions LFD: good overall performance across tests Freely available Princeton Shape Benchmark 1,814 classified polygonal models Source code for evaluation tools Conclusion

Future Work Multi-classifiers Evaluate statistical significance of results Application of techniques to other domains Text retrieval Image retrieval Protein classification

Acknowledgements David Bengali partitioned thousands of models. Ming Ouhyoung and his students provided the light field descriptor. Dejan Vranic provided the CCCC and MPEG-7 databases. Viewpoint Data Labs donated the Viewpoint database. Remco Veltkamp and Hans Tangelder provided the Utrecht database. Funding: The National Science Foundation grants CCR and 11S

The End