LMS News – March 2022
LMS for Open Source: In the recent years, the LMS has published a lot of its research and solutions in open-source repositories. Here is a little selection. First, we would like to mention our “Frequency Selective Reconstruction“, which can reconstruct missing or faulty parts of an image in a very convincing manner. Visually appealing is the data processed by a software that creates depth maps from multi-spectral images (Cross-Spectral Training for Deep-Learning). Concerning audio processing, we published a large dataset which helps in developing localization and tracking algorithms for sound sources (LOCATA Challenge on the IWAENC 2018). In order to visualize distortions induced by Fisheye images, we provide a user-interface based on Python (FishUI). Finally, we just published a toolbox for the evaluation of the compression efficienfy of video codecs.
In the future, we plan to generate more data and software to be released as open source, so that anyone can use it.