Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
复制标题
DOI：
--
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
Giannis Daras;Joseph Dean;A. Jalal;A. Dimakis
中科院分区：
文献类型：
--
作者：
Giannis Daras;Joseph Dean;A. Jalal;A. Dimakis
我们提出了中间层优化（ILO），这是一种新的优化算法，用于解决具有深度生成模型的反问题。而不是只优化初始的潜在代码，我们逐步改变输入层获得连续更有表现力的发电机。为了探索更高的维度空间，我们的方法搜索潜在的代码，位于一个小的l_1 $球周围的前一层诱导的流形。我们的理论分析表明，通过保持球的半径相对较小，我们可以使用深度生成模型来提高压缩感知的既定误差范围。我们的经验表明，我们的方法优于StyleGAN-2和PULSE中引入的最先进的方法，适用于各种逆问题，包括修复，去噪，超分辨率和压缩感知。
We propose Intermediate Layer Optimization (ILO), a novel optimization algorithm for solving inverse problems with deep generative models. Instead of optimizing only over the initial latent code, we progressively change the input layer obtaining successively more expressive generators. To explore the higher dimensional spaces, our method searches for latent codes that lie within a small $l_1$ ball around the manifold induced by the previous layer. Our theoretical analysis shows that by keeping the radius of the ball relatively small, we can improve the established error bound for compressed sensing with deep generative models. We empirically show that our approach outperforms state-of-the-art methods introduced in StyleGAN-2 and PULSE for a wide range of inverse problems including inpainting, denoising, super-resolution and compressed sensing.