发表机构
University of Science and Technology of China; Microsoft Research Asia（中国科学技术大学; 微软亚洲研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对CPU上学习型图像压缩计算开销大的问题，提出PULSE编解码器，采用超低复杂度神经接收器与整数线性熵编码，通过智能体进化优化，在单线程CPU上快速解码并达到与HM相当的压缩性能。
AI 中文摘要
尽管学习型图像压缩近期取得了进展，但现有方法在资源受限的硬件（尤其是CPU）上仍计算开销高昂。我们提出PULSE，一种实用的编解码器，它实现了（1）在多样化硬件平台上的低延迟解码，采用超低复杂度的5.2 kMAC/像素神经接收器，以及（2）利用整数线性CDF预测器和元先验的高效比特精确熵编码。为了在如此紧凑的预算下恢复压缩性能，我们引入了一种由启发式探针引导的智能体进化过程，通过人机（LLM）协作迭代改进架构。PULSE在单线程CPU上解码1080p图像仅需126毫秒，同时实现了与HM相当的压缩性能。经过感知优化后，PULSE可与MS-ILLM等更大规模的感知编解码器竞争。代码见该https URL。
英文摘要
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 on diverse hardware platforms with an ultra-low-complexity 5.2 kMAC/pixel neural receiver, and (2) efficient bit-exact entropy coding with an integer linear CDF predictor and a meta prior. To recover compression performance under this tight budget, we introduce an agentic evolution process guided by heuristic probes that iteratively improves the architecture through human-LLM collaboration. PULSE decodes a 1080p image in 126 ms on a single CPU thread while achieving compression performance comparable to HM. After perceptual optimization, PULSE competes with larger perceptual codecs like MS-ILLM. Codes are at https://github.com/microsoft/GenCodec/tree/main/PULSE
