Fast Nonlinear Image Unblending

Daichi Horita, Kiyoharu Aizawa, Ryohei Suzuki, Taizan Yonetsuji, Huachun Zhu; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 2051-2059


Nonlinear color blending, which is advanced blending indicated by blend modes such as overlay and multiply, is extensively employed by digital creators to produce attractive visual effects. To enjoy such flexible editing modalities on existing bitmap images like photographs, however, creators need a fast nonlinear blending algorithm that decomposes an image into a set of semi-transparent layers. To address this issue, we propose a neural-network-based method for nonlinear decomposition of an input image into linear and nonlinear alpha layers that can be separately modified for editing purposes, based on the specified color palettes and blend modes. Experiments show that our proposed method achieves an inference speed 370 times faster than the state-of-the-art method of nonlinear image unblending, which uses computationally intensive iterative optimization. Furthermore, our reconstruction quality is higher or comparable than other methods, including linear blending models. In addition, we provide examples that apply our method to image editing with nonlinear blend modes. Our code will be made publicly available.

Related Material

@InProceedings{Horita_2022_WACV, author = {Horita, Daichi and Aizawa, Kiyoharu and Suzuki, Ryohei and Yonetsuji, Taizan and Zhu, Huachun}, title = {Fast Nonlinear Image Unblending}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {2051-2059} }