通过重排时间步优化扩散模型，大幅降低计算量且保持图像质量。
Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution
- 分阶段去噪：早期粗略生成，减少冗余计算。
- 时间步重排只需10分钟搜索，实现高效采样路径调整。
- 在CIFAR10和LSUN-Church上节省80%~90%算力，几乎无质量损失。
最近，扩散模型（DMs）在高质量图像生成方面取得了显著进展。然而，多步去噪过程常导致巨大计算开销，阻碍其在资源受限的边缘设备上的部署。现有方法通过压缩模型和调整时间步序列来缓解该问题，但忽略了输入冗余性，且需耗时较长的搜索过程。本文提出一种细粒度到粗粒度的扩散模型（Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution）。针对早期生成图像难以区分的现象，引入细粒度到粗粒度去噪（C2F），减少粗粒度特征生成阶段的计算量；同时设计时间步序列重排（TRD），实现高效的采样轨迹调整，搜索时间少于10分钟。实验表明，所提方法在CIFAR10和LSUN-Church数据集上实现了近无损性能，计算量减少80%至90%。
原文摘要 · Abstract (English)
Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computational overhead, impeding deployment on resource-constrained edge devices. Existing methods mitigate this issue by compressing models and adjusting the time step sequence. However, they overlook input redundancy and require lengthy search times. In this paper, we propose Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution. Recognizing indistinguishable early-stage generated images, we introduce Coarse-to-Fine Denoising (C2F) to reduce computation during coarse feature generation. Furthermore, we design Time Step Sequence Redistribution (TRD) for efficient sampling trajectory adjustment, requiring less than 10 minutes for search. Experimental results demonstrate that the proposed methods achieve near-lossless performance with an 80% to 90% reduction in computation on CIFAR10 and LSUN-Church.
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。