Learning Image Decompression with Convolutional Networks
Convolutional Neural Networks (ConvNets) have shown break-through performance and/or performance-per-power on many computer vision tasks such as classification, image segmentation, optical flow and super-resolution. We think that applying ConvNets for the compression of image data could be a promising approach. For this we would have to think about how we can limit the information capacity of the output signal, e.g. through quantization. A nice aspect of this application is that the usually limited training data is not an issue, since randomly acquired images our the internet can be used to train the network.
In this project, we have developed several ConvNets to remove compression artifacts of strong JPEG compression, essentially creating an improved decompression algorithm.
Thilo Weber, Jonas Wiesendanger
- Looking for 1 Master or (1 or 2) semester project students (work load will be adjusted)
- Contact/Supervision: Lukas Cavigelli
- Decent Matlab and C programming skills
- Motivation for signal processing problems
- Ideally some knowledge of GPU programming
- 20%-30% Theory
- 20%-30% C/CUDA programming
- 50% ConvNet model design (Lua/Torch coding) and evaluation (Matlab)