PalGAN: Image Colorization with Palette Generative Adversarial Networks
This work addresses colorization challenges for image processing applications, offering incremental improvements through novel integration of existing techniques.
The paper tackled the problems of multimodal ambiguity and color bleeding in image colorization by proposing PalGAN, a GAN-based approach with palette estimation and chromatic attention, resulting in outperforming state-of-the-art methods in quantitative and visual evaluations with diverse, contrastive, and edge-preserving outputs.
Multimodal ambiguity and color bleeding remain challenging in colorization. To tackle these problems, we propose a new GAN-based colorization approach PalGAN, integrated with palette estimation and chromatic attention. To circumvent the multimodality issue, we present a new colorization formulation that estimates a probabilistic palette from the input gray image first, then conducts color assignment conditioned on the palette through a generative model. Further, we handle color bleeding with chromatic attention. It studies color affinities by considering both semantic and intensity correlation. In extensive experiments, PalGAN outperforms state-of-the-arts in quantitative evaluation and visual comparison, delivering notable diverse, contrastive, and edge-preserving appearances. With the palette design, our method enables color transfer between images even with irrelevant contexts.