Creating Consistent Scene Graphs Using a Probabilistic Grammar Tianqiang LiuSiddhartha ChaudhuriVladimir G. Kim Qi-Xing HuangNiloy J. MitraThomas Funkhouser.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

Indoor Segmentation and Support Inference from RGBD Images Nathan Silberman, Derek Hoiem, Pushmeet Kohli, Rob Fergus.
Semantic Contours from Inverse Detectors Bharath Hariharan et.al. (ICCV-11)
A Search-Classify Approach for Cluttered Indoor Scene Understanding Liangliang Nan 1, Ke Xie 1, Andrei Sharf 2 1 SIAT, China 2 Ben Gurion University, Israel.
CS460/IT632 Natural Language Processing/Language Technology for the Web Lecture 2 (06/01/06) Prof. Pushpak Bhattacharyya IIT Bombay Part of Speech (PoS)
Ignas Budvytis*, Tae-Kyun Kim*, Roberto Cipolla * - indicates equal contribution Making a Shallow Network Deep: Growing a Tree from Decision Regions of.
Correlation Search in Graph Databases Yiping Ke James Cheng Wilfred Ng Presented By Phani Yarlagadda.
Lauritzen-Spiegelhalter Algorithm
SPONSORED BY SA2014.SIGGRAPH.ORG Annotating RGBD Images of Indoor Scenes Yu-Shiang Wong and Hung-Kuo Chu National Tsing Hua University CGV LAB.
May 2006CLINT-LN Parsing1 Computational Linguistics Introduction Approaches to Parsing.
A Probabilistic Model for Component-Based Shape Synthesis Evangelos Kalogerakis, Siddhartha Chaudhuri, Daphne Koller, Vladlen Koltun Stanford University.
Patch to the Future: Unsupervised Visual Prediction
3D Shape Representation Tianqiang 04/01/2014. Image/video understanding Content creation Why do we need 3D shapes?
Creating Consistent Scene Graphs Using a Probabilistic Grammar Tianqiang LiuSiddhartha ChaudhuriVladimir G. Kim Qi-Xing HuangNiloy J. MitraThomas Funkhouser.
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.
CKY Parsing Ling 571 Deep Processing Techniques for NLP January 12, 2011.
A Graphical Model For Simultaneous Partitioning And Labeling Philip Cowans & Martin Szummer AISTATS, Jan 2005 Cambridge.
Hilbert Space Embeddings of Hidden Markov Models Le Song, Byron Boots, Sajid Siddiqi, Geoff Gordon and Alex Smola 1.
1 Mining Frequent Patterns Without Candidate Generation Apriori-like algorithm suffers from long patterns or quite low minimum support thresholds. Two.
Announcements  Project proposal is due on 03/11  Three seminars this Friday (EB 3105) Dealing with Indefinite Representations in Pattern Recognition.
Randomized Cuts for 3D Mesh Analysis
Learning Low-Level Vision William T. Freeman Egon C. Pasztor Owen T. Carmichael.
Hierarchical Constraint Satisfaction in Spatial Database Dimitris Papadias, Panos Kalnis And Nikos Mamoulis.
Expectation Maximization Algorithm
Graph Cut based Inference with Co-occurrence Statistics Ľubor Ladický, Chris Russell, Pushmeet Kohli, Philip Torr.
Co-training LING 572 Fei Xia 02/21/06. Overview Proposed by Blum and Mitchell (1998) Important work: –(Nigam and Ghani, 2000) –(Goldman and Zhou, 2000)
Object Recognition: Conceptual Issues Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and K. Grauman.
Visual Object Recognition Rob Fergus Courant Institute, New York University
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.
Review Rong Jin. Comparison of Different Classification Models  The goal of all classifiers Predicating class label y for an input x Estimate p(y|x)
Seven Lectures on Statistical Parsing Christopher Manning LSA Linguistic Institute 2007 LSA 354 Lecture 7.
Statistical Natural Language Processing. What is NLP?  Natural Language Processing (NLP), or Computational Linguistics, is concerned with theoretical.
Step 3: Classification Learn a decision rule (classifier) assigning bag-of-features representations of images to different classes Decision boundary Zebra.
Tree Kernels for Parsing: (Collins & Duffy, 2001) Advanced Statistical Methods in NLP Ling 572 February 28, 2012.
DTU Medical Visionday May 27, 2009 Generative models for automated brain MRI segmentation Koen Van Leemput Athinoula A. Martinos Center for Biomedical.
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.
Bayesian Hierarchical Clustering Paper by K. Heller and Z. Ghahramani ICML 2005 Presented by HAO-WEI, YEH.
Why Categorize in Computer Vision ?. Why Use Categories? People love categories!
Organizing Heterogeneous Scene Collections through Contextual Focal Points Kai Xu, Rui Ma, Hao Zhang, Chenyang Zhu, Ariel Shamir, Daniel Cohen-Or, Hui.
Style Compatibility For 3D Furniture Models Tianqiang Liu 1 Aaron Hertzmann 2 Wilmot Li 2 Thomas Funkhouser 1 1 Princeton University 2 Adobe Research.
TEMPLATE DESIGN © Zhiyao Duan 1,2, Lie Lu 1, and Changshui Zhang 2 1. Microsoft Research Asia (MSRA), Beijing, China.2.
ECE 8443 – Pattern Recognition LECTURE 07: MAXIMUM LIKELIHOOD AND BAYESIAN ESTIMATION Objectives: Class-Conditional Density The Multivariate Case General.
CS 782 – Machine Learning Lecture 4 Linear Models for Classification  Probabilistic generative models  Probabilistic discriminative models.
Exploiting Context Analysis for Combining Multiple Entity Resolution Systems -Ramu Bandaru Zhaoqi Chen Dmitri V.kalashnikov Sharad Mehrotra.
September 2007 IW-SMI2007, Kyoto 1 A Quantum-Statistical-Mechanical Extension of Gaussian Mixture Model Kazuyuki Tanaka Graduate School of Information.
Module networks Sushmita Roy BMI/CS 576 Nov 18 th & 20th, 2014.
Randomized Algorithms for Bayesian Hierarchical Clustering
Acquiring 3D Indoor Environments with Variability and Repetition Young Min Kim Stanford University Niloy J. Mitra UCL/ KAUST Dong-Ming Yan KAUST Leonidas.
BARD / April BARD: Bayesian-Assisted Resource Discovery Fred Stann (USC/ISI) Joint Work With John Heidemann (USC/ISI) April 9, 2004.
Multi-Speaker Modeling with Shared Prior Distributions and Model Structures for Bayesian Speech Synthesis Kei Hashimoto, Yoshihiko Nankaku, and Keiichi.
Sponsored by Deformation-Driven Topology-Varying 3D Shape Correspondence Ibraheem Alhashim Kai Xu Yixin Zhuang Junjie Cao Patricio Simari Hao Zhang Presenter:
csa3050: Parsing Algorithms 11 CSA350: NLP Algorithms Parsing Algorithms 1 Top Down Bottom-Up Left Corner.
Lecture 2: Statistical learning primer for biologists
SA2014.SIGGRAPH.ORG SPONSORED BY Automatic Semantic Modeling of Indoor Scenes from Low-quality RGB-D Data using Contextual Information Kang Chen 1 Yu-Kun.
Sai Zhang Michael D. Ernst Google Research University of Washington
October 2005CSA3180: Parsing Algorithms 21 CSA3050: NLP Algorithms Parsing Algorithms 2 Problems with DFTD Parser Earley Parsing Algorithm.
Department of Computer Science The University of Texas at Austin USA Joint Entity and Relation Extraction using Card-Pyramid Parsing Rohit J. Kate Raymond.
Bayesian Hierarchical Clustering Paper by K. Heller and Z. Ghahramani ICML 2005 Presented by David Williams Paper Discussion Group ( )
Automatic 3D modelling of Architecture Anthony Dick 1 Phil Torr 2 Roberto Cipolla 1 1 Department of Engineering 2 Microsoft Research, University of Cambridge.
Tracking Hands with Distance Transforms Dave Bargeron Noah Snavely.
PAC-Bayesian Analysis of Unsupervised Learning Yevgeny Seldin Joint work with Naftali Tishby.
Tree and Forest Classification and Regression Tree Bagging of trees Boosting trees Random Forest.
Naive Bayes Classifier. REVIEW: Bayesian Methods Our focus this lecture: – Learning and classification methods based on probability theory. Bayes theorem.
Prior Knowledge for Part Correspondence
Analysis and design of algorithm
Dorm Room Activity Design a dorm room that is no larger than 180 square feet (12X15) Your room must include the door, a window, and the closet. Use ¼ inch.
Evaluating Logarithms
Introduction to Object Tracking
Human-object interaction
Presentation transcript:

Creating Consistent Scene Graphs Using a Probabilistic Grammar Tianqiang LiuSiddhartha ChaudhuriVladimir G. Kim Qi-Xing HuangNiloy J. MitraThomas Funkhouser 11,23 3, Princeton University Cornell University Stanford University TTICUCL

Motivation Growing number of 3D scenes online. Google 3D warehouse

Motivation Synthesis [Fisher et al 2012, Xu et al 2013] Understanding [Xu et al 2014, Song et al 2014]

Goal Input: A scene from Trimble 3D Warehouse

Goal Output 1: Semantic segmentations

Goal Output 2: Category labels. Door Nightstand Window Mattress Bed frame Pillow Dresser Mirror Heater Artifact

Goal Output 2: Category labels at different levels. Bed & supported Dresser & supported

Goal Sleeping area Vanity area Door set Output 2: Category labels at different levels.

Challenges Shape is not distinctive. Night table Console table

Challenges Contextual information Meeting chair Meeting table Study desk Study chair

Challenges All-pair contextual information is not distinctive. #pairs feet #pairs feet

Challenges

All-pair contextual information is not distinctive. #pairs feet #pairs feet

Key Idea Semantic groups Semantic hierarchy

Key Idea #pairs feet #pairs feet

Pipeline Probabilistic grammar

Related Work Van Kaick et al. 2013

Related Work Van Kaick et al. 2013Boulch et al. 2013

Overview Grammar Structure Learning a Probabilistic Grammar Scene Parsing Results

Probabilistic Grammar Labels Rules Probabilities

Labels bed, night table, sleeping area Examples:

Rules sleeping areabed, night table Example:

Probabilities Derivation probabilities Cardinality probabilities Geometry probabilities Spatial probabilities

Derivation probability bedbed frame, mattress

Cardinality probability sleeping areabed, night table

Geometry probability

Spatial probability

Overview Grammar Structure Learning a Probabilistic Grammar Scene Parsing Results

Pipeline Probabilistic grammar

Learning a Probabilistic Grammar Identify objects Speed X 5

Learning a Probabilistic Grammar Label objects Speed X 5

Learning a Probabilistic Grammar Group objects Speed X 5

Learning a Probabilistic Grammar Grammar generation Labels all unique labels Rules Probabilities

Learning a Probabilistic Grammar Grammar generation Labels Rules concatenating all children for each label Probabilities Nightstand & supported NightstandTable lamp Nightstand & supported NightstandPlant Nightstand & supported NightstandTable lamp Plant Training example 1:Training example 2:

Learning a Probabilistic Grammar Grammar generation Labels Rules Probabilities : learning from occurrence statistics : estimating Gaussian kernels : kernel density estimation

Overview Grammar Structure Learning a Probabilistic Grammar Scene Parsing Results

Pipeline Probabilistic grammar

Pipeline Probabilistic grammar

Scene parsing Objective function is the unknown hierarchy is the input scene is the probabilistic grammar

Scene parsing After applying Bayes’ rule

Scene parsing After applying Bayes’ rule Prior of hierarchy

Scene parsing After applying Bayes’ rule Prior of hierarchy : probability of a single derivation formulated using

Scene parsing After applying Bayes’ rule Prior of hierarchy compensates for decreasing probability as has more internal nodes.

Scene parsing After applying Bayes’ rule Likelihood of scene

Scene parsing After applying Bayes’ rule Likelihood of scene : geometry probability

Scene parsing After applying Bayes’ rule Likelihood of scene : sum of all pairwise spatial probabilities

Scene parsing We work in the negative logarithm space

Scene parsing Rewrite the objective function recursively where is the root of, is the energy of a sub-tree. XX

Scene parsing The search space is prohibitively large … Problem 1: #possible groups is exponential. Problem 2: #label assignments is exponential.

Scene parsing Problem 1: #possible groups is exponential. ……… ………

Solution: proposing candidate groups. Scene parsing ……… ………

Rule: a a c c d d b b a a d d b b c c b b d d a a c c c c a a d d b b … Problem 2: #label assignments is exponential.

Scene parsing Problem 2: #label assignments is exponential. Solution: bounding #RHS by grammar binarization … … where is partial label of

Scene parsing Problem 2: #label assignments is exponential. Solution: bounding #RHS by grammar binarization … where … Now #rules and #assignments are both polynomial. The problem can be solved by dynamic programming. is partial label of

Scene parsing Problem 2: #label assignments is exponential. Solution: bounding #RHS by grammar binarization Convert the result to a parse tree of the original grammar

Overview Grammar Structure Learning a Probabilistic Grammar Scene Parsing Results

Benefit of hierarchy Meeting table Shape only Study chair

Benefit of hierarchy Shape only Flat grammar Meeting chair Meeting table Study chair

Benefit of hierarchy Shape only Flat grammar Study chair Study desk Meeting chair Meeting table Ours Meeting table Study chair

Benefit of hierarchy Shape only Flat grammar Meeting chair Meeting table Ours Study area Meeting area Meeting table Study chair

Benefit of hierarchy Shape only Chair Mattress Console table

Benefit of hierarchy Shape onlyFlat grammar Chair Nightstand Console table Mattress Console table

Benefit of hierarchy Shape onlyFlat grammarOurs Chair Nightstand Console table Mattress Console table Chair Desk

Benefit of hierarchy Shape onlyFlat grammarOurs Chair Nightstand Console table Mattress Console table Study area Sleep area

Datasets 77 bedrooms30 classrooms8 libraries 17 small bedrooms8 small libraries

Benefit of hierarchy Object classification

Generalization of our method Parsing Sketch2Scene data set

Take-away message Modeling hierarchy improves scene understanding.

Limitation and Future Work Modeling correlation in probabilistic grammar.

Limitation and Future Work Modeling correlation in probabilistic grammar. Grammar learning from noisy data. Sleep area bed Nightstand & supported Nightstand Table lamp Input scene graphsGrammar

Limitation and Future Work Applications in other fields. Modeling correlation in probabilistic grammar. Grammar learning from noisy data. Modeling from RGB-D data [Chen et al. 2014]

Acknowledgement Data Kun Xu Discussion Christiane Fellbaum, Stephen DiVerdi Funding NSF, ERC Starting Grant, Intel, Google, Adobe

Code and Data

Back up slides

Learning a Probabilistic Grammar Creating a training set manually 1.Identify leaf-level objects. 2.Provide a label for each object in a scene. 3.Group objects and provide group labels. 4.Maintain consistency. Sleeping area Nightstand & supported NightstandTable lamp Sleeping area Nightstand & supported Nightstand … …

Sensitivity analysis Impact of training set size Impact of energy terms

Benefit of hierarchy Object classification Object grouping