Optimizing Intermediate Representations of Generative Models for Phase Retrieval

• URL: http://arxiv.org/abs/2205.15617v1
• Date: Tue, 31 May 2022 09:01:15 GMT
• Title: Optimizing Intermediate Representations of Generative Models for Phase Retrieval
• Authors: Tobias Uelwer, Sebastian Konietzny, Stefan Harmeling
• Abstract summary: Phase retrieval is the problem of reconstructing images from magnitude-only measurements. We use a novel variation of intermediate layer optimization (ILO) to extend the range of the generator while still producing images consistent with the training data.
• Score: 0.5156484100374059
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Phase retrieval is the problem of reconstructing images from magnitude-only measurements. In many real-world applications the problem is underdetermined. When training data is available, generative models are a new idea to constrain the solution set. However, not all possible solutions are within the range of the generator. Instead, they are represented with some error. To reduce this representation error in the context of phase retrieval, we first leverage a novel variation of intermediate layer optimization (ILO) to extend the range of the generator while still producing images consistent with the training data. Second, we introduce new initialization schemes that further improve the quality of the reconstruction. With extensive experiments on Fourier and Gaussian phase retrieval problems and thorough ablation studies, we can show the benefits of our modified ILO and the new initialization schemes.

Related papers

• Convergence Properties of Score-Based Models for Linear Inverse Problems Using Graduated Optimisation [44.99833362998488]
  We show that score-based generative models (SGMs) can be used to solve inverse problems. We show that we are able to recover high-Ms images, independent of the initial value. The source is publicly available on GitHub.
  arXiv  Detail & Related papers  (2024-04-29T13:47:59Z)
• Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
  Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs. In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
  arXiv  Detail & Related papers  (2023-11-20T08:27:56Z)
• DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion [144.9653045465908]
  We propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM) Our approach yields promising fusion results in infrared-visible image fusion and medical image fusion.
  arXiv  Detail & Related papers  (2023-03-13T04:06:42Z)
• Variational Laplace Autoencoders [53.08170674326728]
  Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. We present a novel approach that addresses the limited posterior expressiveness of fully-factorized Gaussian assumption. We also present a general framework named Variational Laplace Autoencoders (VLAEs) for training deep generative models.
  arXiv  Detail & Related papers  (2022-11-30T18:59:27Z)
• Alternating Phase Langevin Sampling with Implicit Denoiser Priors for Phase Retrieval [1.7767466724342065]
  We present a way leveraging the prior implicitly learned by a denoiser to solve phase retrieval problems by incorporating it in a classical framework. Compared to performant denoising-based algorithms for phase retrieval, we showcase competitive performance with notable measurements on in-distribution images and notable out-of-distribution images.
  arXiv  Detail & Related papers  (2022-11-02T05:08:50Z)
• DOLPH: Diffusion Models for Phase Retrieval [19.22990916056669]
  Phase retrieval refers to the problem of recovering an image from the magnitudes of its complex-valued linear measurements. Since the problem is ill-posed, recovery requires prior knowledge on unknown image. We present as a new deep model-based for phase retrieval that reconstructs an image prior to a diffusion step.
  arXiv  Detail & Related papers  (2022-11-01T15:31:34Z)
• Denoising Diffusion Restoration Models [110.1244240726802]
  Denoising Diffusion Restoration Models (DDRM) is an efficient, unsupervised posterior sampling method. We demonstrate DDRM's versatility on several image datasets for super-resolution, deblurring, inpainting, and colorization.
  arXiv  Detail & Related papers  (2022-01-27T20:19:07Z)
• Learning Discriminative Shrinkage Deep Networks for Image Deconvolution [122.79108159874426]
  We propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms. Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.
  arXiv  Detail & Related papers  (2021-11-27T12:12:57Z)
• Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
  Blind image restoration is a common yet challenging problem in computer vision. We propose a novel blind image restoration method, aiming to integrate both the advantages of them. Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
  arXiv  Detail & Related papers  (2020-08-25T03:30:53Z)
• DeepInit Phase Retrieval [10.385009647156407]
  This paper shows how data deep generative models can be utilized to solve challenging phase retrieval problems. It shows that our hybrid approach is able to deliver very high reconstruction results at low sampling rates.
  arXiv  Detail & Related papers  (2020-07-16T09:39:28Z)
• u-net CNN based fourier ptychography [5.46367622374939]
  We propose a new retrieval algorithm that is based on convolutional neural networks. Experiments demonstrate that our model achieves better reconstruction results and is more robust under system aberrations.
  arXiv  Detail & Related papers  (2020-03-16T22:48:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.