Posts

I was in Paris last week in order to give some lectures for a continuous training curriculum where I teach mostly 3D reconstruction and optical flow computation. Preparing these lessons has kept me busy a few nights, but we had again this year some very positive feedback about our way of teaching those sometimes complex matters. A huge part of our students satisfaction comes from the many demos that we’re using to illustrate the various formula that pop up during the lessons.

When starting with Deep Learning on your own (without any legacy code or compatibility constraint), it may be daunting to choose one among the many frameworks available.

[Update 22.03.2018: link to correct Youtube publication.]

U-Net was proposed in 2015 for medical image segmentation. You can find the original paper, along with some video introduction on the project homepage. Its structure is relatively simple and shallow, so it seems to be well fitted for a learning work.

It turns out I completed my PhD in 2012 just before Deep Learning started to boom and be the Next Big Thing in Computer Vision. The various pieces were already there (neural networks, back propagation, large scale databases, GPGPU…), but still, I somehow managed to slip through it. Later at work, I’ve used standard Pattern Recognition approaches for realtime applications, and later the more complex and efficient Gradient Boosted Trees, but still, no luck at trying Deep Learning.

I’m restarting this blog after keeping it quiet for a few years. What changes to expect? Well, quite a bit: I’m back to Computer Vision, playing with photogrammetry pipelines, meshes, classifiers… I’m moving into product management this blog is now published thanks to hugo with the Academic theme the comments are disabled, but you can interact through the contact address or directly via social networks. I’ve been lucky (and grateful) to attend new events and meet new communities last year, primarily at ISPRS (Hannover) and the Product Management Festival in Zürich.

Story of a bug that I introduced in my codebase while making it parallel.

A quick tip for people who have some troubles compiling OpenCV 3.0 alpha on MacOS X.

This is (finally) a follow-up to my latest post!

Ooops, it’s already end of May and… the first post for 2014.

The Non-Local Means algorithm 1 is a very popular image denoising algorithm. Besides its efficiency at denoising, it’s also one of the main causes to the non-locality trend that has arisen in Image Processing conferences ever since. Yet, there is this recent paper on Arxiv 2: Non-Local means is a local image denoising algorithm by Postec, Froment and Vedel. Some background on NL-means NL-means is a very simple, yet highly efficient image denoising algorithm that preserves well image textures even with severe noise.