a probabilistic model for component-based shape synthesis
DESCRIPTION
A Probabilistic Model for Component-Based Shape Synthesis. Evangelos Kalogerakis , Siddhartha Chaudhuri , Daphne Koller , Vladlen Koltun Stanford University. Bayesian networks. Directed acyclic graph (DAG) Nodes – random variables Edges – direct influence (“causation”) - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/1.jpg)
A Probabilistic Model for Component-Based Shape Synthesis
Evangelos Kalogerakis, Siddhartha Chaudhuri, Daphne Koller, Vladlen Koltun
Stanford University
![Page 2: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/2.jpg)
SP2-2
Bayesian networks• Directed acyclic graph (DAG)
– Nodes – random variables– Edges – direct influence (“causation”)
• Xi ? Xancestors | Xparents
• e.g., C ? {R,B,E} | A• Simplifies chain rule by using
conditional independencies
Earthquake Burglary
AlarmRadio
Pearl, 1988
Call
![Page 3: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/3.jpg)
Goal
• A tool that automatically synthesizes a variety of new, distinct shapes from a given domain.
![Page 4: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/4.jpg)
Sailing ships vary in:
- Size
- Type of hull, keel and mast
- The number and configuration of masts.
Various geometric, stylistic and functional relationships influence the selection and placement of individual components to ensure that the final shape forms a coherent whole.
![Page 5: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/5.jpg)
Probabilistic Reasoning for Assembly-Based 3D Modeling
Siddhartha Chaudhuri, Evangelos Kalogerakis, Leonidas Guibas, and Vladlen Koltun
ACM Transactions on Graphics 30(4) (Proc. SIGGRAPH), 2011
![Page 6: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/6.jpg)
![Page 7: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/7.jpg)
The probabilistic model is flat!!!!
It describes the relationship among components, but it does NOT tells us how these components form the whole structure.
![Page 8: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/8.jpg)
Offline Learning
Online shape synthesis
![Page 9: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/9.jpg)
The model structure
R - shape style
S = {Sl} - component style per category l
N = {Nl} - number of components from category l.
C = {Cl} - continuous geometric feature vector for components from category l. (curvature histograms, shape diameter histograms, scale parameters, spin images, PCA-based descriptors, and lightfield descriptors)
D = {Dl} - discrete geometric feature vector for components from category l. (encode adjacency information.)
![Page 10: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/10.jpg)
For 4-legged table:Ntop=1 or 2;Nleg=4;Stop=rectangular tabletopsSleg=narrow column-like legs
For 1-legged tableNtop=1Nleg=1Stop=roughly circular tabletopsSleg=split legs
![Page 11: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/11.jpg)
Learning
• The input:– A set of K compatibly segmented shapes. – For each component, we compute its geometric
attributes. – The training data is thus a set of feature vectors: – O = {O1,O2, . . . ,Ok}, where Ok = {Nk,Dk,Ck}.
• The goal – learn the structure of the model (domain sizes of latent
variables and lateral edges between observed variables) and the parameters of all CPDs in the model.
![Page 12: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/12.jpg)
The desired structure G is the one that has highest probability given input data O [Koller and Friedman 2009]. By Bayes’ rule, this probability can be expressed as
Max P(G|O) -- > Max P (O | G)
![Page 13: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/13.jpg)
Assume prior distributions over the parameters Θ of the model.
parameter priors
summing over all possible assignments to the latent variables R and S:the number of integrals is exponentially large !!!
![Page 14: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/14.jpg)
To make the learning procedure computationally tractable, they use an effective approximation of the marginal likelihood known as the Cheeseman-Stutz score [Cheeseman and Stutz 1996]:
a fictitious dataset that comprises the training data O and approximate statistics for the values of the latent variables.
the parameters estimated for a given G
The score defines a metric to measure how good a model is.
The goal is to search a G maximize the score!
![Page 15: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/15.jpg)
What does the G mean?
The number of table styles (R)
Whether a category of components belongs to a specific style? What is the number? (S)
![Page 16: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/16.jpg)
Greedy Structure search
• Initially, set the domain size of 1 for R (a single shape style).
• for each category l,– Set the component style as 1, compute the score, then 2, 3,
…, stop when the score decreases. The local maximal value is the style number of l. Move the next category.
• After the search iterates over all variables in S, increase the domain size of R and repeat the procedure.
• terminates when the score reaches a local maximum that does not improve over 10 subsequent iterations;
![Page 17: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/17.jpg)
Domain size of R =1• All tables belong to the same style.• For leg:
– Compute the score for case 1: all legs are of the same style;– Compute the score for case 2: narrow column-like legs and split
legs.– Compute the score for case 3: three styles of legs. Score decreases
so stop.• For table-top:
– …
![Page 18: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/18.jpg)
CPT of R
1 2
5/12 7/12
CPT of Stop (R=1)
1 2
1.0 0.0
CPT of Stop (R=2)
1 2
0.0 1.0
CPT of Sleg (R=1)
1 2
1.0 0.0
CPT of Sleg (R=2)
1 2
0.0 1.0
…
![Page 19: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/19.jpg)
Shape Synthesis
• Step 1: Synthesizing a set of components
1-legged or 4-legged
Rect or circular?
column-like or split
Pruning: Branches that contain assignments that have extremely low probability density
![Page 20: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/20.jpg)
Shape Synthesis
• Step 1: Synthesizing a set of components• Step 2: Optimizing component placement
“slots” specify where this component can be attached to other components.
![Page 21: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/21.jpg)
Shape Synthesis
• Step 1: Synthesizing a set of components• Step 2: Optimizing component placement
penalizes discrepancies of position and relative size between each pair of adjacent slots
![Page 22: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/22.jpg)
Shape Synthesis
• Step 1: Synthesizing a set of components• Step 2: Optimizing component placement
![Page 23: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/23.jpg)
Application: Shape database amplification
• synthesize all instantiations of the model that have non-negligible probability– identify and reject instantiations that are very
similar to shapes in the input dataset or to previous instantiations. (by measuring the feature vectors of corresponding components)
![Page 24: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/24.jpg)
Application: Constrained shape synthesis
• Give partial assignments to constrained random variables assume values only from the range corresponding to the specified constraints.
4-leg
split
![Page 25: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/25.jpg)
Results• Learning took about 0.5 hours for construction vehicles, 3
hours for creatures, 8 hours for chairs, 20 hours for planes, and 70 hours for ships.
• For shape synthesis, enumerating all possible instantiations of a learned model takes less than an hour in all cases, and final assembly of each shape takes a few seconds.
![Page 26: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/26.jpg)
![Page 27: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/27.jpg)
![Page 28: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/28.jpg)
![Page 29: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/29.jpg)
![Page 30: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/30.jpg)
![Page 31: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/31.jpg)
Can it generate models like below?
or
The probability should be very low.
or
![Page 32: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/32.jpg)
Inspiration- Variability vs plausibility
• To maintain plausibility: should be similar to the existing ones;• To increase variability: should be as different as possible from
the existing ones.• This work is good for maintaining plausibility but the variability
seems low.• How to pursue large variability while maintaining plausibility?
or
![Page 33: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/33.jpg)
Topic? Generating shape variation by variability transfer
• learn the varying model in the dataset rather than the shape model.
• Use the varying model to synthesize new shape in another dataset.
![Page 34: A Probabilistic Model for Component-Based Shape Synthesis](https://reader035.vdocument.in/reader035/viewer/2022062813/568165c0550346895dd8c49e/html5/thumbnails/34.jpg)
Topic? function-preserved shape synthesize
• The function of a component is not taken into account in the current model…
• By considering function, we can create variations with high dissimilarity on geometric looking while preserve the function.