Non-locality and NL-Means Non-locality is a powerful recent paradigm in Image Processing that was introduced around 2005. Put in simple words, it consists in considering that an image is a collection of highly redundant patches. In this context, pixels get described by the surrounding patch instead of their sole value), and patch relationships are only deduced from their visual similarity (thus ignoring their spatial relationship).
Non-locality comes in two flavors: exemplar-based 1 or sparsity-based.
The end of 2012… Good and bad news But not only. Starting on January 1st, 2013, I won’t be a research assistant anymore.
So, good news or bad news ?
Goods news is, I’ve found a job, so I have to leave. Bad news is, well, we you have a real day job, you can’t really spend a lot of time on your personal research, including writing a thesis.
Here are some short reading notes of a paper that came out on arXiv this week. I have a few RSS feeds positioned there, and I was immediately caught by the title:
Inverting and Visualizing Features for Object Detection
by Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz and Antonio Torralba (MIT/CSAIL).
The paper What is it about ? As the title says, it’s about feature inversion and visualization. Yes, but not any feature: the now ubiquitous HOG feature.
In mid-November, I’ve been attending the ICPR 2012 conference in Tsukuba (Japan). It was a first time for me at a more “Pattern recognition”-oriented conference, with a slightly different community of attendees than ICIP or ICASSP, and also a different organization. I’ve been a bit suprised to have the feeling that the French community was bigger and more homogeneous than in these 2 conferences.
ICPR’12 facts About the conference, I liked the fact that there were less sessions in parallel than ICIP or ICASSP1, so it’s actually a bit easier to attend various sessions.
OK, it’s been a while again, but here are the reasons for being silent.
1-bit LBD reconstruction is out! Remember all those posts about LBDs, FREAKs, BRIEFs, and reconstructing images ? The latest version of tis work is out with a major feature: 1-bit quantized LBDs reconstruction. Yes, 1-bit !
To achieve this, we leverage some results from 1-bit Compressed Sensing thanks to my co-author Laurent Jacques.
So, the pre-print is on arxiv and on infoscience, and you can get the code from github.
So, we have seen first that using Matlab and CUDA together was not always straightforward, especially on a Mac. Then, I showed a simple project to demonstrate how to do it in practice. In this post, we’re going to see how to compile this project using a Makefile.
Final part : the Makefile! Overview of the compilation process Let’s recap the different steps needed to compile our mex file :