15862 Final Project  - Object Modeling with Layers.

-Charudatta Phatak

cphatak@andrew.cmu.edu

 

Link to the paper (pdf)

Link to presentation (ppt)

 

Section 1: Layered PCA model

 

Regular appearance models build a statistical model of an object describing its shape and texture. However when we have objects in which the certain landmark/features are completely absent, it poses a problem for constructing a model. Eg. Cars.

 

 

 

 

 

 

 

 


Figure 1. Features like license plate are completely absent in first 2 cars. Fog lights are absent in the first car but present in the second car.

 

So we separate the objects into different layers corresponding to each feature. We then construct the model for each layer. This way we can account for the absence of a layer by putting weights.

 

 

 

 

 

 

 

 

 

 

 

 


Figure 2. Image showing different layers.

 


     (a)                                                   (b)

 

 

 

 

 

 

 

 

Figure 3. (a) Novel car image constructed by random sampling through the layered PCA model. (b) Similar image constructed using regular model.

 

 

   (a)                                                                       (b)

 

 

 

 

 

 

 

 

 

 

 

Figure 4. (a) Original car. (b) Adding a license plate to the car.

 

 

 

 


      (a)                                                                      (b)

 

 

 

 

 

 

 

 

 

 

Figure 5. (a) Original Car. (b) Replacing the grill of the car.

 

Section 2: LLE model

 

PCA model is based on the least square method which minimizes the cost of reconstruction. We can improve this by using LLE model, which uses only nearest neighbor information for reconstruction of images. We calculate the reconstruction weights and then compute the lower dimensional space coordinates from the weights.

 

 

 

 

 

 

 

 

 

 

 

 

 


Figure 6. Algorithm for LLE.

 

 


           (a)                                                          (b)

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Figure 7. Comparison of LLE with PCA. The images on top show the points plotted using first 2 coordinates of PCA and the bottom two images for LLE. (a) Comparison shown by Roweis et al. (b) Similar comparison for car data set.