Yan, S; Qiu, X; Liao, Q; Xue, JH; Liu, S; (2024) Reschedule Diffusion-based Bokeh Rendering. In: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. (pp. pp. 1543-1551). IJCAI

Preview

Text 0171.pdf - Accepted Version Download (6MB) | Preview

Abstract

Bokeh rendering for images shot with small apertures has drawn much attention in practice.Very recently people start to explore diffusion models for bokeh rendering, aiming to leverage the models' surging power of image generation.However, we can clearly observe two big issues with the images rendered by diffusion models: large fluctuation and severe color deviation.To address these issues, we propose in this paper a prior-aware sampling approach, which can adaptively control the noise scale through learned priors, and a prior-aware noise scheduling strategy, which can greatly reduce the number of inference steps without sacrificing performance. Extensive experiments show that our method can effectively alleviate the fluctuation problem of sampling results while ensuring similar color styles to the input image.In addition, our method outperforms state-of-the-art methods, sometimes even with only two steps of sampling.Our code is available at https://github.com/Loeiii/Reschedule-Diffusion-based-Bokeh-Rendering.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as CSVJSONXML

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item