Written on 06.01.2021 11:46 by Anna Kukleva
You are welcome to design your own project or adapt from the ones below.
The deadline for the project is February 8. You will need to submit a report, the example you can find here.
Before January 11 choose the project and write a timeline, when you plan to do what. Send this to tutors with the subject [PGM project].
Every week you are required to send a short email with what has been done and what is the plan for the next steps.
Predicting text from 3x4 numeric keypad inputs (T9)
Given an input by a user (e.g. 1 2 2) build a model that can predict what the user wants to express (e.g. add or bee or bed).
A simple solution will condition the output on the input of the last letter, yet it might be more powerful to incorporate specific user statistics as well and condition on previous (or in hindsight even following) words.
Image denoising with spatially dependent noise and color channels
Multiple problems can be solved:
Denoising of spatially dependent noise
Denoising images of various types of sources (e.g. color images or x-ray medical images)
Image segmentation to partition an image into segments
(for example on: archive.ics.uci.edu/ml/datasets/image+segmentation)
Assumption: data is governed by a number of latent variables (topics)
The task would be to train a graphical topic model, for instance
On images (visual topics)
On text documents (semantic topics)
Probabilistic game playing agent
Train a graphical model representing a stochastic game, such as Blackjack (one or more players)
Local statistical shape model:
Build local statistical shape models for each part of the body and define a graph that connects the parts to produce coherent shapes. The graph structure can be a tree or with loops.
The end goal is then to sample from the graph to produce realistic shapes with more variation than using a global shape model.
http://smpl.is.tue.mpg.de/ (server might be down for 1-2 days)
Shape registration using distributed inference:
Given two 3D shapes (for example of humans), split the shapes into parts and find the alignment between them. In the lecture exercises you have found the registration by treating the shape as a whole. In this project the idea is to consider the shape as a union of weakly connected parts. The goal is to find the optimal alignment by designing an energy function that can be decomposed into unaries (part registration cost) and pairwise terms (part to part cost).
3D pose and shape estimation using particle message passing:
Using a variation of particle filters for graphs track the human pose and shape of people in images. The human pose of the person is represented in 3D as a collection of loosely connected parts.
Given low-res and high-res training images your task is create an algorithm that output high-res image for the input low-res images.
For the reference you can use this paper:
Your task is to create algorithm on images or videos to separate background from foreground.
As dataset for images you can use CIFAR or Mini-ImageNet.
For videos Weizman dataset. ( videos you can dowload from here: http://www.wisdom.weizmann.ac.il/~vision/SpaceTimeActions.html)
As a refernece for the algorithm you can use GrubCat alg. https://cvg.ethz.ch/teaching/cvl/2012/grabcut-siggraph04.pdf
The task is to segment images into semanticaly meaningful segments.
For the task use Pacal VOC 2010 dataset.
Reference paper: http://jamie.shotton.org/work/publications/ijcv07a.pdf
Sample code to work with 3D human shapes: