Progressive color transfer with dense semantic correspondences
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Article number | 13 |
Journal / Publication | ACM Transactions on Graphics |
Volume | 38 |
Issue number | 2 |
Online published | 6 Apr 2019 |
Publication status | Published - Apr 2019 |
Link(s)
Abstract
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.
Research Area(s)
- Color, Deep matching, Transfer
Bibliographic Note
Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).
Citation Format(s)
Progressive color transfer with dense semantic correspondences. / He, Mingming; Liao, Jing; Chen, Dongdong; Yuan, Lu; Sander, Pedro V.
In: ACM Transactions on Graphics, Vol. 38, No. 2, 13, 04.2019.Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review