用简单几何与纹理模型生成合成图像，提升图像修复网络的性能与可解释性。
VibrantLeaves: A principled parametric image generator for training deep restoration models
- 基于几何建模与成像简化原则构建合成图像生成器
- 在合成数据上训练的模型达到自然图像水平的修复效果
- 生成数据具旋转缩放不变性，增强模型鲁棒性
本文提出一种基于少数基本原理的合成图像生成器，聚焦几何建模、纹理与成像过程的简化模拟。这些原则融合经典死叶模型，生成高质量图像修复训练数据。在该数据集上训练的标准去噪与超分辨率网络，性能可媲美在自然图像上训练的结果。该方法旨在解决深度神经网络在图像修复中因缺乏理解与天然图像数据偏见带来的问题。通过控制训练集，尤其采用合成与抽象数据，实现更好可解释性。研究还分析各原理影响，明确维持高性能所需的关键图像属性，并揭示模型天然继承生成数据的旋转与尺度不变性，提升鲁棒性。
原文摘要 · Abstract (English)
In this paper, we introduce a synthetic image generator relying on a few simple principles, specifically focusing on geometric modeling, textures, and a simple modeling of image acquisition. These principles, integrated into the classical Dead Leaves model, allow for the creation of high-quality training sets for image restoration tasks. Standard image denoising and super-resolution networks trained on these datasets achieve performance comparable to those trained on natural image datasets. The motivation behind this approach stems from the limitations of Deep Neural Networks in image restoration tasks. Despite their impressive performance, these networks are often poorly understood and prone to biases inherited from standard natural image training sets. To mitigate these issues, we emphasize the need for a better control over training sets, particularly through the use of synthetic and abstract datasets. Furthermore, our work includes a detailed analysis of the principles considered, identifying which image properties are necessary for maintaining high performance, thus taking a first step towards explainability. Besides, we show that neural networks trained with our synthetic sets naturally inherit robustness to the invariance properties of these sets, namely rotation and scale.
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。