DeCompress：通过神经压缩进行去噪
DeCompress: Denoising via Neural Compression
AI总结：
提出一种基于神经压缩的去噪算法DeCompress，无需真实图像和大型数据集，仅需单张噪声图像即可训练，且对过拟合鲁棒，性能优于零样本和无监督去噪器。
摘要：
基于学习的去噪算法在各种去噪任务中实现了最先进的性能。然而，训练此类模型依赖于获取由干净图像和噪声图像对组成的大型训练数据集。另一方面，在许多成像应用中，例如显微镜成像，收集真实图像（ground truth）通常不可行。为了解决这一挑战，研究人员最近开发了无需访问真实数据即可训练的算法。然而，训练此类模型在计算上仍然具有挑战性，并且仍然需要访问大量噪声训练样本。在这项工作中，受基于压缩的去噪和神经压缩近期进展的启发，我们提出了一种新的基于压缩的去噪算法，命名为DeCompress，该算法：i）不需要访问真实图像，ii）不需要访问大型训练数据集——仅需单个噪声图像即可，iii）对过拟合具有鲁棒性，iv）与零样本或基于无监督学习的去噪器相比，实现了更优越的性能。
英文摘要：
Learning-based denoising algorithms achieve state-of-the-art performance across various denoising tasks. However, training such models relies on access to large training datasets consisting of clean and noisy image pairs. On the other hand, in many imaging applications, such as microscopy, collecting ground truth images is often infeasible. To address this challenge, researchers have recently developed algorithms that can be trained without requiring access to ground truth data. However, training such models remains computationally challenging and still requires access to large noisy training samples. In this work, inspired by compression-based denoising and recent advances in neural compression, we propose a new compression-based denoising algorithm, which we name DeCompress, that i) does not require access to ground truth images, ii) does not require access to large training dataset - only a single noisy image is sufficient, iii) is robust to overfitting, and iv) achieves superior performance compared with zero-shot or unsupervised learning-based denoisers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
