Image restoration (IR) has been an indispensable and challenging task in the low-level
vision field, which strives to improve the subjective quality of images distorted by various …

Diffusion models have demonstrated impressive performance in various image generation,
editing, enhancement and translation tasks. In particular, the pre-trained text-to-image stable …

We introduce ToonCrafter, a novel approach that transcends traditional correspondence-
based cartoon video interpolation, paving the way for generative interpolation. Traditional …

Image and video colorization are among the most common problems in image restoration.
This is an ill-posed problem and a wide variety of methods have been proposed, ranging …

Deep generative models have garnered significant attention in low-level vision tasks due to
their generative capabilities. Among them, diffusion model-based solutions, characterized by …

Video colorization poses challenging tasks, necessitating structural stability, continuity, and
details control in the colors produced. In this paper, based on a pretrained text-to-image …

Due to the richness of natural image semantics, natural image colourisation is a challenging
problem. Existing methods often suffer from semantic confusion due to insufficient semantic …