Structural Consistency and Controllability for Diverse Colorization
This work addresses structural artifacts in colorization for media and advertising, offering incremental improvements over existing methods.
The paper tackled the problem of structural inconsistency in diverse image colorization by developing a conditional random field based variational auto-encoder that incorporates structural consistency and controllability, achieving more diverse and globally consistent colorizations on datasets like LFW, LSUN-Church, and ILSVRC-2015.
Colorizing a given gray-level image is an important task in the media and advertising industry. Due to the ambiguity inherent to colorization (many shades are often plausible), recent approaches started to explicitly model diversity. However, one of the most obvious artifacts, structural inconsistency, is rarely considered by existing methods which predict chrominance independently for every pixel. To address this issue, we develop a conditional random field based variational auto-encoder formulation which is able to achieve diversity while taking into account structural consistency. Moreover, we introduce a controllability mecha- nism that can incorporate external constraints from diverse sources in- cluding a user interface. Compared to existing baselines, we demonstrate that our method obtains more diverse and globally consistent coloriza- tions on the LFW, LSUN-Church and ILSVRC-2015 datasets.