用强化学习优化扩散模型，提升遥感图像超分辨率效果
ORL-LDM: Offline Reinforcement Learning Guided Latent Diffusion Model Super-Resolution Reconstruction
- 在扩散模型反向去噪中引入强化学习框架，用PPO优化生成策略
- 在RESISC45数据集上PSNR提升3-4dB，SSIM改善0.08-0.11，LPIPS降低0.06-0.10
- 适合处理复杂自然场景的遥感图像超分辨率，尤其擅长细节保留
随着遥感技术的快速发展，超分辨率图像重建具有重要的研究与应用价值。现有深度学习方法虽取得进展，但在复杂场景处理和细节保持方面仍存在局限。本文提出一种基于强化学习的潜在扩散模型（LDM）微调方法，用于遥感图像超分辨率重建。该方法构建包含状态、动作和奖励的强化学习环境，在LDM模型的反向去噪过程中采用近端策略优化（PPO）算法优化决策目标。在RESISC45数据集上的实验表明，相比基线模型，该方法在PSNR、SSIM和LPIPS指标上均有显著提升，其中PSNR提高3-4dB，SSIM提升0.08-0.11，LPIPS下降0.06-0.10，尤其在结构化和复杂自然场景中表现优异。结果验证了该方法在提升超分辨率质量及跨场景适应性方面的有效性。
原文摘要 · Abstract (English)
With the rapid advancement of remote sensing technology, super-resolution image reconstruction is of great research and practical significance. Existing deep learning methods have made progress but still face limitations in handling complex scenes and preserving image details. This paper proposes a reinforcement learning-based latent diffusion model (LDM) fine-tuning method for remote sensing image super-resolution. The method constructs a reinforcement learning environment with states, actions, and rewards, optimizing decision objectives through proximal policy optimization (PPO) during the reverse denoising process of the LDM model. Experiments on the RESISC45 dataset show significant improvements over the baseline model in PSNR, SSIM, and LPIPS, with PSNR increasing by 3-4dB, SSIM improving by 0.08-0.11, and LPIPS reducing by 0.06-0.10, particularly in structured and complex natural scenes. The results demonstrate the method's effectiveness in enhancing super-resolution quality and adaptability across scenes.
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。