通过相位引导渐进剪枝，实现高效图像超分辨率。
PGP-DiffSR: Phase-Guided Progressive Pruning for Efficient Diffusion-based Image Super-Resolution
- 基于输入相位信息逐步剪裁冗余模块，保留修复能力。
- 在保持高质量重建的同时，显著降低计算与内存开销。
- 适合资源受限场景下的高效图像超分辨率应用。
尽管基于扩散模型的图像超分辨率取得了优异效果，但其通常依赖大型主干网络（如 Stable Diffusion XL 和 Diffusion Transformers），导致训练和推理时计算与内存开销过大。为此，我们提出轻量级扩散方法 PGP-DiffSR，通过输入相位信息引导，去除扩散模型中的冗余信息，实现高效图像超分辨率。首先，识别扩散主干内部块级冗余，提出渐进式剪枝策略，在保留修复能力的前提下移除冗余块。发现剪枝后模型对重建图像的相位估计不佳，因此设计相位交换适配模块，利用输入相位信息指导剪枝模型提升恢复性能。将渐进剪枝与相位交换适配模块统一建模。大量实验表明，该方法在显著降低计算负载与内存消耗的同时，仍能实现具有竞争力的重建质量。代码已公开于 https://github.com/yzb1997/PGP-DiffSR。
原文摘要 · Abstract (English)
Although diffusion-based models have achieved impressive results in image super-resolution, they often rely on large-scale backbones such as Stable Diffusion XL (SDXL) and Diffusion Transformers (DiT), which lead to excessive computational and memory costs during training and inference. To address this issue, we develop a lightweight diffusion method, PGP-DiffSR, by removing redundant information from diffusion models under the guidance of the phase information of inputs for efficient image super-resolution. We first identify the intra-block redundancy within the diffusion backbone and propose a progressive pruning approach that removes redundant blocks while reserving restoration capability. We note that the phase information of the restored images produced by the pruned diffusion model is not well estimated. To solve this problem, we propose a phase-exchange adapter module that explores the phase information of the inputs to guide the pruned diffusion model for better restoration performance. We formulate the progressive pruning approach and the phase-exchange adapter module into a unified model. Extensive experiments demonstrate that our method achieves competitive restoration quality while significantly reducing computational load and memory consumption. The code is available at https://github.com/yzb1997/PGP-DiffSR.
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。