English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we present an approach to image enhancement with diffusionmodel in underwater scenes. Our method adapts conditional denoising diffusionprobabilistic models to generate the corresponding enhanced images by using theunderwater images and the Gaussian noise as the inputs. Additionally, in orderto improve the efficiency of the reverse process in the diffusion model, weadopt two different ways. We firstly propose a lightweight transformer-baseddenoising network, which can effectively promote the time of network forwardper iteration. On the other hand, we introduce a skip sampling strategy toreduce the number of iterations. Besides, based on the skip sampling strategy,we propose two different non-uniform sampling methods for the sequence of thetime step, namely piecewise sampling and searching with the evolutionaryalgorithm. Both of them are effective and can further improve performance byusing the same steps against the previous uniform sampling. In the end, weconduct a relative evaluation of the widely used underwater enhancementdatasets between the recent state-of-the-art methods and the proposed approach.The experimental results prove that our approach can achieve both competitiveperformance and high efficiency. Our code is available at\href{mailto:https://github.com/piggy2009/DM_underwater}{\color{blue}{https://github.com/piggy2009/DM\_underwater}}.

Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip Strategy