arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1802.07079stat.ML
收藏

结构不确定性预测网络

Structured Uncertainty Prediction Networks

University of Bath(巴斯大学);Anthropics Technology Ltd.(Anthropics科技有限公司);University College London(伦敦大学学院)

Gara Dorta, Sara Vicente, Lourdes Agapito, Neill D. F. Campbell, Ivor Simpson

AI总结:

本文首次提出预测合成图像结构不确定性分布的网络,通过学习全高斯协方差矩阵实现高效采样和似然评估,用于图像重建和去噪。

摘要:

本文首次提出预测合成图像结构不确定性分布的网络。以往的方法多局限于预测对角协方差矩阵。我们的新模型学习为每个重建预测完整的高斯协方差矩阵,从而实现高效的采样和似然评估。我们证明了该模型能够准确重建合成数据集中的真实相关残差分布,并为真实人脸图像生成合理的高频样本。我们还展示了如何利用这些预测的协方差进行结构保持的图像去噪。

英文摘要:

This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image. Previous approaches have been mostly limited to predicting diagonal covariance matrices. Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits efficient sampling and likelihood evaluation. We demonstrate that our model can accurately reconstruct ground truth correlated residual distributions for synthetic datasets and generate plausible high frequency samples for real face images. We also illustrate the use of these predicted covariances for structure preserving image denoising.

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。

↑