用多变量先验模型提升图像重建精度与速度。
Multivariate Fields of Experts for Convergent Image Reconstruction
- 引入基于ℓ∞范数的多变量势函数，改进图像先验学习。
- 在去噪、去模糊等任务中优于单变量模型，接近深度学习效果。
- 结构清晰可解释，收敛有理论保证，适合医疗成像等关键场景。
我们提出多变量领域专家框架，用于学习图像先验。该模型通过ℓ∞-范数的Moreau包络构建多变量势函数，推广了现有领域专家方法。在图像去噪、去模糊、压缩感知磁共振成像和计算机断层扫描等多种逆问题中验证了有效性。相比同类单变量模型，本方法性能更优，且接近深度学习正则化表现，同时参数更少、训练数据需求更低、推理更快。此外，模型因结构化设计具备高可解释性，并拥有理论收敛保证，确保在敏感重建任务中的可靠性。
原文摘要 · Abstract (English)
We introduce the multivariate fields of experts, a new framework for the learning of image priors. Our model generalizes existing fields of experts methods by incorporating multivariate potential functions constructed via Moreau envelopes of the $\ell_\infty$-norm. We demonstrate the effectiveness of our proposal across a range of inverse problems that include image denoising, deblurring, compressed-sensing magnetic-resonance imaging, and computed tomography. The proposed approach outperforms comparable univariate models and achieves performance close to that of deep-learning-based regularizers while being significantly faster, requiring fewer parameters, and being trained on substantially fewer data. In addition, our model retains a high level of interpretability due to its structured design. It is supported by theoretical convergence guarantees which ensure reliability in sensitive reconstruction tasks.
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。