2018/05/18 · We propose a manifold localized deep external compensation (MALDEC) network to additionally utilize reference images, i. e., retrieved similar ...

We propose a MAnifold Localized Deep External Compensation (MALDEC) network to additionally utilize reference images, ie retrieved similar images in cloud ...

The learnable components of MALDEC, internal structure inference, and external compensation, are trained jointly to make a good tradeoff between these two terms ...

We propose a manifold localized deep external compensation (MALDEC) network to additionally utilize reference images, i. e., retrieved similar images in cloud ...

"Reference Guided Deep Super-Resolution via Manifold Localized External Compensation", Accepted by IEEE Trans. on Circuit System for Video Technology (TCSVT) ...

Reference-guided deep super-resolution via manifold localized external compensation. W Yang, S Xia, J Liu, Z Guo. IEEE Transactions on Circuits and Systems ...

Reference-guided deep super-resolution via manifold localized external compensation. W Yang, S Xia, J Liu, Z Guo. IEEE Transactions on Circuits and Systems ...

This paper proposes a novel multi-reference based SR method. We first propose a coarse-to-fine warping method to warp the references with the LR input.

Reference Guided Deep Super-Resolution via Manifold Localized External Compensation Wenhan Yang, Sifeng Xia, Jiaying Liu, and Zongming Guo Accepted by IEEE ...

Reference-Guided Deep Super-Resolution via Manifold Localized External Compensation ... This paper proposes a manifold localized deep external compensation ...