研究人员开发了两种新框架 SlimDiffSR 和 TOC-SR，以提高扩散模型在图像超分辨率任务中的效率。SlimDiffSR 专注于遥感图像，使用蒸馏教师模型和结构化剪枝技术，实现了高达 200 倍的推理加速和 20 倍的参数减少。TOC-SR 通过特征级蒸馏和架构发现创建紧凑型扩散骨干网络，在蒸馏成单步生成器之前，参数减少了 6.6 倍，GMACs 减少了 2.8 倍。这两种方法都旨在平衡高重建质量与显著降低的计算成本，以实现实际部署。 AI
影响 这些进展通过降低计算要求，可能促进扩散模型在图像增强任务中的更广泛应用。
排序理由 两篇新研究论文介绍了提高图像超分辨率扩散模型效率的方法。
AI 生成摘要 · Google Gemini · 来自 9 个来源。 我们如何撰写摘要 →
arXiv:2605.03399v1 Announce Type: new Abstract: Probabilistic super-resolution of high-dimensional spatial fields using diffusion models is often computationally prohibitive due to the cost of operating directly in pixel space. We propose PODiff, a structured conditional generati…
arXiv:2410.17966v3 Announce Type: replace-cross Abstract: In recent years, diffusion models have emerged as a superior alternative to generative adversarial networks (GANs) for high-fidelity image generation, with wide applications in text-to-image generation, image-to-image tran…
arXiv:2505.00334v3 Announce Type: replace Abstract: Image Super-Resolution is a fundamental problem in computer vision with broad applications spacing from medical imaging to satellite analysis. The ability to reconstruct high-resolution images from low-resolution inputs is cruci…
arXiv:2506.23566v2 Announce Type: replace Abstract: The acquisition of high-resolution satellite imagery is often constrained by the spatial and temporal limitations of satellite sensors, as well as the high costs associated with frequent observations. These challenges hinder app…
arXiv:2601.17723v2 Announce Type: replace Abstract: Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). To date, no empirical study has systematically examined the effectiveness of existing methods, nor investig…
arXiv:2605.02198v1 Announce Type: new Abstract: Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffS…
arXiv:2605.02767v1 Announce Type: new Abstract: Diffusion models have recently demonstrated strong performance for image restoration tasks, including super-resolution. However, their large model size and iterative sampling procedures make them computationally expensive for practi…
Diffusion models have recently demonstrated strong performance for image restoration tasks, including super-resolution. However, their large model size and iterative sampling procedures make them computationally expensive for practical deployment. In this work, we present TOC-SR,…
Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a lightweight and efficient diffusion-based f…