110 papers with code • 1 benchmarks • 6 datasets
Colorization is the process of adding plausible color information to monochrome photographs or videos. Colorization is a highly undetermined problem, requiring mapping a real-valued luminance image to a three-dimensional color-valued one, that has not a unique solution.
Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9. 89 and FID of 2. 20, a competitive likelihood of 2. 99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
Over the last decade, the process of automatic image colorization has been of significant interest for several application areas including restoration of aged or degraded images.
Furthermore, the joint intensity-gradient constraint in data-fidelity term is proposed to limit the degree of freedom within generative model at the iterative colorization stage, and it is conducive to edge-preserving.