Progressive Color Transfer with Dense Semantic Correspondences
This work addresses the problem of accurate color transfer for images with similar semantics, which is incremental as it builds on existing methods by incorporating dense semantic matching and joint optimization.
The authors tackled color transfer between images with similar semantic structures by proposing an algorithm that uses neural representations for dense semantic correspondences and optimizes a local linear model with local and global constraints, achieving accurate results validated on diverse image content.
We propose a new algorithm for color transfer between images that have perceptually similar semantic structures. We aim to achieve a more accurate color transfer that leverages semantically-meaningful dense correspondence between images. To accomplish this, our algorithm uses neural representations for matching. Additionally, the color transfer should be spatially variant and globally coherent. Therefore, our algorithm optimizes a local linear model for color transfer satisfying both local and global constraints. Our proposed approach jointly optimizes matching and color transfer, adopting a coarse-to-fine strategy. The proposed method can be successfully extended from one-to-one to one-to-many color transfer. The latter further addresses the problem of mismatching elements of the input image. We validate our proposed method by testing it on a large variety of image content.