Name
Abstract | ||
|---|---|---|
This paper proposes a new colour transfer method with Optimal transport to transfer the colour of a source image to match the colour of a target image of the same scene. We propose to formulate the problem in higher dimensional spaces (than colour spaces) by encoding overlapping neighborhoods of pixels containing colour information as well as spatial information. Since several recoloured candidates are now generated for each pixel in the source image, we define an original procedure to efficiently merge these candidates which allows denoising and artifact removal as well as colour transfer. Experiments show quantitative and qualitative improvements over previous colour transfer methods. Our method can be applied to different contexts of colour transfer such as transferring colour between different camera models, camera settings, illumination conditions and colour retouch styles for photographs. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.23919/EUSIPCO.2019.8902611 | 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO) |
Keywords | Field | DocType |
optimal transport, colour transfer, image enhancement, JPEG compression blocks | Noise reduction,Spatial analysis,Computer vision,Computer science,Pixel,Artificial intelligence,Merge (version control),Encoding (memory) | Conference |
ISSN | Citations | PageRank |
2076-1465 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hana Alghamdi | 1 | 0 | 0.34 |
| Mairead Grogan | 2 | 11 | 3.94 |
| Rozenn Dahyot | 3 | 340 | 32.62 |