Algorithm for Lensless Camera
Researchers at Indian Institute of Technology (IIT), Madras and US-based Rice University have together developed algorithms for lensless and miniature cameras. The deep learning algorithm is capable of producing photo-realistic images fro the blurred lensless capture. Lensless cameras have several applications including Augmented Reality (AR), Virtual Reality (VR), security, smart wearables and robotics where cost, form-factor, and weight become major constraints. Existing algorithms to deblur images based on traditional optimisation schemes yield low-resolution 'noisy images'. Kaushik Mitra, Department of Electrical Engineering, IIT-M and Prof Ashok Veeraraghavan of Rice University who led the team said that they used 'Deep Learning' to develop a reconstruction algorithm called FlatNet. This was tested on various real and challenges scenarios and found to be effective in de-blurring images.