Flex-DDCM：基于扩散轨迹引导的零样本任务导向图像压缩
Flex-DDCM: Zero-Shot Task-Oriented Image Compression via Diffusion Trajectory Guidance
用预训练扩散模型做零样本压缩，不用专门训练就能按下游任务调整重建方向。跟 Diff-ICMH 比，解码更快，还能和训练过的任务导向编解码器打平。做图像传输和机器视觉落地的工程师可以看看。
一篇新论文提出 Flex-DDCM，一种面向任务的零样本图像压缩框架，无需压缩专用训练即可重建图像。该框架在 Turbo-DDCM 的基础上改造编码扩散轨迹，通过任务引导的噪声选择把任务引导的效果嵌入压缩表示，引导项可单独或组合使用，并用随时间步变化的强度控制去噪全程的影响。
这套设计的核心优势是任务适配不增加额外解码复杂度，能在像素保真度、感知质量和下游任务性能之间灵活权衡。实验显示其性能可与经过训练的任务导向编解码器竞争，且解码速度快于 Diff-ICMH。对于需要在同一码流下同时服务人眼观看和机器分析的场景，这提供了一种免训练的方案。
Flex-DDCM: Zero-Shot Task-Oriented Image Compression via Diffusion Trajectory Guidance
Recent zero-shot image compression methods exploit the powerful priors of pretrained diffusion models to produce perceptually pleasing reconstructions without compression-specific training. However, image compression serves not only human viewing but also machine analysis, while existing zero-shot codecs have limited flexibility in meeting the diverse reconstruction requirements of these applications. In this paper, we propose Flex-DDCM, a framework for zero-shot task-oriented image compression via diffusion trajectory guidance. Building on Turbo-DDCM, we adapt the coded diffusion trajectory through task-guided noise selection, embedding the effects of task guidance into the compressed representation. Guidance terms can be applied individually or combined, with timestep-dependent strengths controlling their influence throughout denoising. This design enables task adaptation without introducing additional decoding complexity. Experiments demonstrate flexible trade-offs among pixel fidelity, perceptual quality, and downstream task performance, with competitive performance against trained task-oriented codecs and faster decoding than Diff-ICMH.
本条情报归属 AITOP「论文」核心追踪栏目。涉及核心实体与技术议题包括：Flex-DDCM、Turbo-DDCM、图像压缩、扩散模型，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Yixin Gao, Runsen Feng, Xin Li, Zhibo Chen），经 AITOP 多维评分管线结构化提炼。