|国家预印本平台
首页|UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

来源:Arxiv_logoArxiv
英文摘要

Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands. We present UltraPixel, a novel architecture utilizing cascade diffusion models to generate high-quality images at multiple resolutions (\textit{e.g.}, 1K to 6K) within a single model, while maintaining computational efficiency. UltraPixel leverages semantics-rich representations of lower-resolution images in the later denoising stage to guide the whole generation of highly detailed high-resolution images, significantly reducing complexity. Furthermore, we introduce implicit neural representations for continuous upsampling and scale-aware normalization layers adaptable to various resolutions. Notably, both low- and high-resolution processes are performed in the most compact space, sharing the majority of parameters with less than 3$\%$ additional parameters for high-resolution outputs, largely enhancing training and inference efficiency. Our model achieves fast training with reduced data requirements, producing photo-realistic high-resolution images and demonstrating state-of-the-art performance in extensive experiments.

Haoyu Chen、Long Peng、Jingjing Ren、Wenbo Li、Lei Zhu、Bin Shao、Yong Guo、Renjing Pei、Fenglong Song

计算技术、计算机技术

Haoyu Chen,Long Peng,Jingjing Ren,Wenbo Li,Lei Zhu,Bin Shao,Yong Guo,Renjing Pei,Fenglong Song.UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks[EB/OL].(2024-07-02)[2025-08-02].https://arxiv.org/abs/2407.02158.点此复制

评论