无需重训练，加速图像压缩模型推理速度超13倍。
Wavefront Parallelization for Efficient Learned Image Compression
- 基于视频编码的波前并行思想，重构推理顺序以减少串行步骤。
- 在保持原有率失真性能前提下，实现超过13倍的推理加速。
- 适合已有预训练模型的快速部署，尤其适用于实时图像压缩场景。
自回归上下文模型是学习型图像压缩的基础，但其推理过程存在串行效率低的问题。现有加速方法如棋盘状上下文需修改网络结构并重新训练，无法用于预训练模型。本文提出一种完全无需训练的推理阶段加速算法，灵感来自视频编码标准中的波前并行技术。该方法将推理过程重新组织为最优的“错位”波前顺序，在保持精确自回归依赖关系的前提下最小化串行步骤。实验表明，该方法可使预训练的自回归模型（如Cheng等人）推理速度提升超过13倍，同时维持原始率失真性能。此外，通过适度放宽上下文依赖精度，还可实现更快的解码。源代码将发布于https://github.com/tokkiwa/compressai-wavefront。
原文摘要 · Abstract (English)
Autoregressive context models are foundational for learned image compression,but they suffer from slow serial inference. Existing acceleration methods such as checkerboard context require architectural changes and retraining, thus are inapplicable to pre-trained models. We propose a completely training-free inference-time acceleration algorithm inspired by wavefront parallelism in video coding standards. Our method reorganizes inference into an optimal ``staggered'' wavefront order, minimizing sequential steps while maintaining exact autoregressive dependencies. Experimental results show our approach accelerates pre-trained autoregressive models (e.g., Cheng et al.) by more than $13\times$ while preserving the original rate-distortion performance. We also demonstrate that faster decoding is possible by trading off precise context dependencies. Source code will be available at https://github.com/tokkiwa/compressai-wavefront.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。