This repository is a (Matlab) implementation of the IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) paper:
Intrinsic Image Transfer for Illumination Manipulation.
[Junqing Huang], [Michael Ruzhansky, [Qianying Zhang], [Haihui Wang],
[email protected], [email protected], [email protected], [email protected]
[Abstract:]
This paper presents a novel intrinsic image transfer (IIT) algorithm for image illumination manipulation, which creates a local image translation between two illumination surfaces. We also demonstrate its versatility and benefits to several illumination-related tasks: illumination compensation, image enhancement and tone mapping, and high dynamic range (HDR) image compression, and show their high-quality results on natural image datasets.
- Image tone mapping
(a) Input (b) Ours (c) Exemplar
- Photorealistic style transfer
(a) Input (b) Ours (c) Exemplar (d) Reference style
If you have any questions or suggestions, feel free to reach me ([email protected]).
More details will be uploaded later!