English(EN) PULSE: Unlocking Practical Image Compression on Single-Thread CPU

PULSE 图像压缩通过人机 LLM 协作实现低延迟 CPU 解码

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-17 04:00

研究人员开发了 PULSE，一种专为单线程 CPU 高效解码而设计的新型图像压缩方法。该系统采用超低复杂度神经网络接收器和整数线性 CDF 预测器，实现位精确熵编码。通过涉及人机 LLM 协作的代理演化过程，PULSE 在单 CPU 线程上实现了 126 毫秒内 1080p 图像的低延迟解码，并且在感知优化后，其压缩性能可与 HM 和 MS-ILLM 等成熟编解码器相媲美。 AI

影响这一发展可能在资源受限的设备上实现更高效的图像压缩，可能影响移动应用和边缘计算。

排序理由这是一篇详细介绍新图像压缩方法的论文。[lever_c_demoted from research: ic=1 ai=0.7]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 8 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍新图像压缩方法的论文。[lever_c_demoted from research: ic=1 ai=0.7]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Zhaoyang Jia, Tianyu Zhang, Zihan Zheng, Wenxuan Xie, Jiahao Li, Bin Li, Houqiang Li, Yan Lu · 2026-09-17 04:00

PULSE：在单线程CPU上实现实用的图像压缩

arXiv:2609.18602v1 Announce Type: new Abstract: Despite recent progress in learned image compression, existing methods remain computationally expensive on resource-constrained hardware, particularly CPUs. We introduce PULSE, a practical codec that enables (1) low-latency decoding…

本文如何被排名

报道来源 [1]

PULSE：在单线程CPU上实现实用的图像压缩

相关实体

相关话题