Optimal Image Transport on Sparse Dictionaries
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image-to-Image TranslationStyle TransferSimilar Papers 제목 키워드 기반
Optimal dictionary for least squares representation
Dictionaries are collections of vectors used for representations of random vectors in Euclidean spaces. Recent research on optimal dictionaries is focused on constructing dictionaries that offer sparse representations, i…
A complete characterization of optimal dictionaries for least squares representation
Dictionaries are collections of vectors used for representations of elements in Euclidean spaces. While recent research on optimal dictionaries is focussed on providing sparse (i.e., $\ell_0$-optimal,) representations, h…
Exploring the Effect of Sparse Recovery on the Quality of Image Superresolution
Dictionary learning can be used for image superresolution by learning a pair of coupled dictionaries of image patches from high-resolution and low-resolution image pairs such that the corresponding pairs share the same s…
Dictionary LearningLUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery
Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dictionaries whose features are not directl…
Hyperspectral Image Super-Resolution via Non-Local Sparse Tensor Factorization
Hyperspectral image(HSI)super-resolution, which fuses a low-resolution (LR) HSI with a high-resolution (HR) multispectral image (MSI), has recently attracted much attention. Most of the current HSI super-resolution appro…
Hyperspectral Image Super-ResolutionImage Super-ResolutionSuper-Resolution