State-of-the-art image processing techniques developed here in Adelaide

The Adelaide Machine Learning Group has developed a unified image processing technique based on Deep Learning, which can be applied to various image enhancement tasks such as, not limited to, Image Denoising, Image Inpainting, Image Super-resolution, Image Deblur.

This work will be presented at The Thirtieth Annual Conference on Neural Information Processing Systems (NIPS), Spain, in Dec. 2016. NIPS is arguably the number one Machine Learning conference. More details can be found in the paper: Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections.

The following two images demonstrate an example of recovering clean photos from defocused photos (1st: defocused photo; 2nd: recovered photo).

blurred image

recovered image by our method

This entry was posted in deep learning, publications, research. Bookmark the permalink.

Comments are closed.