Optimal Image Transport on Sparse Dictionaries
This work addresses image transformation problems for computer vision applications, but it is incremental as it combines existing sparse representation and optimal transport methods.
The paper tackles image-to-image translation by developing an optimal transport algorithm over sparse dictionaries, which simultaneously represents and transforms image features like color and style, achieving plausible photo-realistic results in tasks such as color transform and artistic style transfer.
In this paper, we derive a novel optimal image transport algorithm over sparse dictionaries by taking advantage of Sparse Representation (SR) and Optimal Transport (OT). Concisely, we design a unified optimization framework in which the individual image features (color, textures, styles, etc.) are encoded using sparse representation compactly, and an optimal transport plan is then inferred between two learned dictionaries in accordance with the encoding process. This paradigm gives rise to a simple but effective way for simultaneous image representation and transformation, which is also empirically solvable because of the moderate size of sparse coding and optimal transport sub-problems. We demonstrate its versatility and many benefits to different image-to-image translation tasks, in particular image color transform and artistic style transfer, and show the plausible results for photo-realistic transferred effects.