arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.25463cs.CV
收藏

基于区间的方法:用于图像生成加速的协作解码

CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration

Zhejiang University(浙江大学);Shanghai Jiao Tong University(上海交通大学)

Keming Ye, Zhou Zhao, Fan Wu, Shengyu Zhang

AI总结:

本文提出CIAR框架,通过设备端自验证处理图像生成中的大词汇量和空间冗余问题,采用连续概率区间加速处理并保持图像质量,实验显示在速度和云请求减少方面优于现有方法。

摘要:

基于区间的方法:用于图像生成加速的协作解码

英文摘要:

Auto-regressive (AR) models have recently made notable progress in image generation, achieving performance comparable to diffusion-based approaches. However, their computational intensity and sequential nature impede on-device deployment, causing disruptive latency. We address this via a cloud-device collaboration framework \textbf{CIAR}, which utilizes on-device self-verification to handle two key properties of visual synthesis: \textit{the vast token vocabulary} required for high-fidelity images and \textit{inherent spatial redundancy} which leads to extreme predictability in homogeneous regions, while object boundaries exhibit high uncertainty. Uniform verification wastes resources on such redundant tokens. Our solution centers on an on-device token uncertainty quantifier, which adopts continuous probability intervals to accelerate processing and make it feasible for large visual vocabularies instead of conventional discrete solution sets. Additionally, we incorporate a Interval-enhanced decoding module to further speed up decoding while maintaining visual fidelity and semantic consistency via a distribution alignment training strategy. Extensive experiments demonstrate that CIAR achieves a 2.18x speed-up and reduces cloud requests by 70\%, while preserving image quality compared to existing methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑