The Best Demo of ICME 2019 was awarded to Yuan Gao (Kiel University, Germany), Reinhard Koch (Kiel University, Germany), Robert Bregovic (Tampere University, Finland) and Atanas Gotchev (Tampere University, Finland) for their demo “Light Field Reconstruction Using Shearlet Transform in TensorFlow”. The award was presented at the IEEE International Conference on Multimedia and Expo (ICME 2019) in Shanghai, China in July 2019.
With around 1,000 submissions and 500 participants each year, ICME has been the flagship multimedia conference since 2000. It serves as a platform for the experts in the area to promote and discuss the latest advances in multimedia technologies, systems, and applications from both the research and development perspectives.
Abstract:
Shearlet Transform (ST) is one of the most effective approaches for light field reconstruction from Sparsely-Sampled Light Fields (SSLFs). This demo paper presents a comprehensive implementation of ST for light field reconstruction using one of the most popular machine learning libraries, i.e. TensorFlow. The flexible architecture of TensorFlow allows for the easy deployment of ST across different platforms (CPUs, GPUs, TPUs) running varying operating systems with high efficiency and accuracy.
