ComPhoto
Computational Photography, Fall 2011
 Forum 

Jump to...

project #2
final project
assignments

project #1: Edge-Aware Filtering

Assigned: 2011/10/20
Due: 2011/11/09 11:59pm

Project description

In the class, we have introduced a bunch of edge-aware filtering: bilateral [1], WLS [2], Local extrema [3], Diffusion map [4], Domain transform [5], Local Laplacian [6], L0 minimization [7] and Guided filter [8]. In this assignment, you have three options. For the first option, you have to implement one of Local extrema or Diffusion map (which do not have their source codes released). You are free to use any language of your choice. For the second option, you can implement one of the following filters, bilateral, WLS, Guided filter, Domain transform, local Laplacian and L0 minimization (which have made their matlab codes publically available) with a language other than matlab. In the third option, you are asked to compare at least three of the following filters, bilateral, WLS, Guided filter, Domain transform, local Laplacian and L0 minimization (which have made their code publically available). Note that, since these options have different levels of difficulty, option #1 has the highest baseline grade, followed by option #2 and option #3 has the lowest. You are asked to use detail manipulation as the example to illustrate your filter or to compare filters. Other applications will be counted as bonus.

For the first option and the second option, please at least show your results on the following flower image.


For the third option, you have to compare at least three filters with public matlab codes on the application of detail enhancement. Note that you might need to modify some source codes for this purpose. For this application, please at least use the above flower image and the following rock image for comparisons. More filters and more applications are counted as bonus.


You can either work alone or in a team of size two. You need to have my permission first if you want to work in a team of more than two members.

Submission

If you choose option #1 or #2, you need to turn in your source code and a html report which shows your results, applications and discussions.
For option #3, you need to turn in a html report to present the comparison and discussion.
Please submit your project through this website. If you are within cmlab domain, use this one instead.

Reference

  1. S. Paris and F. Durand, A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach, IJCV 2009. (matlab code)
  2. Z. Farbman, R. Fattal, D. Lischinski, R. Szeliski, Edge-Preserving Decompositions for Multi-Scale Tone and Detail Manipulation, SIGGRAPH 2008. (matlab code)
  3. K. Subr, C. Soler, F. Durand, Edge-Preserving Multiscale Image Decomposition Based on Local Extrema, SIGGRAPH Asia 2009.
  4. Z. Farbman, R. Fattal, D. Lischinski, Diffusion Maps for Edge-Aware Image Editing, SIGGRAPH Asia 2010.
  5. E. Gastal, M. Oliveira, Domain Transform for Edge-Aware Image and Video Processing, SIGGRAPH 2011. (matlab code)
  6. S. Paris, S. Hasinoff, J. Kautz, Local Laplacian Filters: Edge-Aware Image Processing with a Laplacian Pyramid, SIGGRAPH 2011. (matlab code)
  7. L. Xu, C. Lu, Y. Xu, J. Jia, Image smoothing via L0 Gradient Minimization, SIGGRAPH Asia 2011. (matlab code)
  8. K. He, J. Sun, X. Tang, Guided Image Filtering, ECCV 2010. (matlab code)