改进自回归模型，用更优采样像素提升图像重建质量
Enhancing Neural Autoregressive Distribution Estimators for Image Reconstruction
- 提出改进版卷积自回归模型，适配真实值与彩色图像
- 均匀覆盖采样像素比随机采样重建效果更好
- 适合图像修复、低样本重建等场景研究者参考
自回归模型通过将D维密度函数分解为一维条件分布的乘积来学习图像数据分布。每个条件分布依赖于先前变量（图像中即为像素），变量处理顺序对模型性能至关重要。本文研究在仅观测部分像素（称作像素块）时，预测图像未观测部分的问题。我们提出一种适用于实值与彩色图像的广义卷积神经自回归分布估计（ConvNADE）模型。同时，我们探究了在随机像素块与基于准蒙特卡洛理论设计的低差异像素块下图像重建的质量。基准数据集上的实验表明，在允许条件下，保持均匀覆盖的像素采样或存储可显著提升重建保真度与测试性能。
原文摘要 · Abstract (English)
Autoregressive models are often employed to learn distributions of image data by decomposing the $D$-dimensional density function into a product of one-dimensional conditional distributions. Each conditional depends on preceding variables (pixels, in the case of image data), making the order in which variables are processed fundamental to the model performance. In this paper, we study the problem of observing a small subset of image pixels (referred to as a pixel patch) to predict the unobserved parts of the image. As our prediction mechanism, we propose a generalized version of the convolutional neural autoregressive distribution estimation (ConvNADE) model adapted for real-valued and color images. Moreover, we investigate the quality of image reconstruction when observing both random pixel patches and low-discrepancy pixel patches inspired by quasi-Monte Carlo theory. Experiments on benchmark datasets demonstrate that, where design permits, pixels sampled or stored to preserve uniform coverage improves reconstruction fidelity and test performance.
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。