用不确定性引导的扰动提升图像重建细节质量
U-DAVI: Uncertainty-Aware Diffusion-Prior-Based Amortized Variational Inference for Image Reconstruction
- 训练时根据不确定度在关键区域注入自适应扰动
- 重建效果优于或媲美现有扩散模型，且无需迭代优化
- 适合需要快速高质量图像重建的应用场景
图像重建中的病态逆问题因退化观测到清晰图像的映射不唯一而难以解决。基于扩散的生成先验虽有潜力，但通常依赖计算量大的迭代采样或针对每组观测值重新优化。近端变分推断框架通过学习测量值到后验分布的直接映射，实现快速后验采样，避免了每次新观测都需优化后验的问题。然而，该方法在恢复细粒度细节和复杂纹理方面仍有不足。为此，本文在训练中引入由不确定性估计指导的空间自适应扰动，强化对不确定区域的学习。在去模糊与超分辨率任务上的实验表明，该方法性能优于或媲美以往扩散基方法，在保持高逼真度重建的同时，避免了迭代精炼的计算开销。
原文摘要 · Abstract (English)
Ill-posed imaging inverse problems remain challenging due to the ambiguity in mapping degraded observations to clean images. Diffusion-based generative priors have recently shown promise, but typically rely on computationally intensive iterative sampling or per-instance optimization. Amortized variational inference frameworks address this inefficiency by learning a direct mapping from measurements to posteriors, enabling fast posterior sampling without requiring the optimization of a new posterior for every new set of measurements. However, they still struggle to reconstruct fine details and complex textures. To address this, we extend the amortized framework by injecting spatially adaptive perturbations to measurements during training, guided by uncertainty estimates, to emphasize learning in the most uncertain regions. Experiments on deblurring and super-resolution demonstrate that our method achieves superior or competitive performance to previous diffusion-based approaches, delivering more realistic reconstructions without the computational cost of iterative refinement.
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。