Lior Shapira

Please use the menubar on top, or the direct links on the right side of the page for quick access to various parts of my website. Enjoy!

Clicking the mosaic will take you to a set of photographs I took in Kyoto and Tokyo during my recent trip to ICCV 2009

I recently returned from ICCV 2009, where I presented a paper by Ariel Shamir, Shai Avidan and myself. The paper is titled ‘Mode-detection via Median-shift’ and deals with very fast clustering of large high-dimensional data sets. Our paper was part of the poster sessions, and it was the first time I’ve presented a poster at a vision conference. It was a very intense experience, over three hours of explaining and demonstrating our work to small groups of people. In the end I was completely exhausted but happy with the level of interest shown. In the project page you can download the paper and the poster, and hopefully soon some version of our software.

I’ve attended most of the sessions and overall I was impressed with the quality of papers presented. My two favorite papers were Super-resolution from a Single Image by Glasner, Bagon and Irani, and Building Rome in a Day by Agarwal et al.

I’m teaching introductory computer graphics again in the fall semester next year, I’ve prepared an introductory page (as always) which can be reached by clicking the banner below…

Spring semester is ending (wiping sweat from brow) and summer is rolling around. And when I say rolling I mean rolling over me with its 35c and 100% humidity… excellent!

Its been a nice semester, I think both my courses went quite well. I was very pleased with the quality of work the students of my graphics course submitted (Examples here and here), and my Java students were also a nice bunch of people. Publication-wise I’m also quite happy. The paper I worked on with Shai Avidan at Adobe has been accepted to ICCV09 (Hurrah!). You can see the project page, it contains some interesting links in addition to the paper.

This summer I have two interesting projects to complete (all very hush hush of course), and lots of going to the beach with Shachar

Well, I’ve returned from Eurographics where I presented ‘Image Appearance Exploration by Model-based Navigation’. The paper was well received and we got the 2nd best paper award. I’ve updated the project page with my Eurographics presentation and in the next few days I’ll update the demo application.

In other news, there’s a growing interest in my SDF (Shape-diameter function) work, so I created a project page here. This page links to the segmentation/skeletonization/part-retrieval application, and has the complete SDF bibliography.

The fall semester is coming to a close and soon the bidding will begin on the spring semester courses. This semester I’m teaching Computer Graphics again. Last year I taught it for the first time and it was a lot of fun, forced me to re-learn a few things. For the students it was pretty damn hard, but I think there was a lot to be learned and I was very happy with the projects students created.

What will be different this time around?

• The semester is longer (last year there was a faculty strike) so I’m probably going to beef up the image processing and animation section (last year I had to skip animation).
• Last year students implemented three projects: Seam Carving, a Ray Tracer and a cute QBert 3D game. This year I have new fiendish ideas which I’ll reveal in due time.
• Last year, partly due to the strike I was very flexible and accommodating with the deadlines. This year I’m going to have to be more strict. Project submission dates will be published well in advance and they will be fixed.

A paper I wrote with Arik and Danny has been accepted to EG ’09. The paper is title ‘Image Appearance Exploration by Model Based Navigation’ and you can see the project page here.

The paper can be broadly categorized as an image processing paper, it deals with changing the appearance of an image by changing its colors. We tackle two major issues. The first one is how to model color changes in an image, and synthesize a new one with no (or little) artifacts. The second is how do we empower a user to make these changes? In most cases the user doesn’t have a well established desired outcome, and even if he does, getting there is a very tiresome trial and error process.

We model color changes using a Gaussian Mixture Model on the image’s colors, and present an innovative gallery based user interface which lets users explore through variations of an image, until they reach a desired result.

Hello virtual theoretical readers! I’ve decided to re-design my academic webpage, and instead of writing everything myself I’m using WordPress. I won’t be doing too much blogging, but I will maintain pages with the courses I’m teaching, papers I’ve published and other vegetables.  Have fun!