English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Phase retrieval is the problem of reconstructing images from magnitude-onlymeasurements. In many real-world applications the problem is underdetermined.When training data is available, generative models allow optimization in alower-dimensional latent space, hereby constraining the solution set to thoseimages that can be synthesized by the generative model. However, not allpossible solutions are within the range of the generator. Instead, they arerepresented with some error. To reduce this representation error in the contextof phase retrieval, we first leverage a novel variation of intermediate layeroptimization (ILO) to extend the range of the generator while still producingimages consistent with the training data. Second, we introduce newinitialization schemes that further improve the quality of the reconstruction.With extensive experiments on the Fourier phase retrieval problem and thoroughablation studies, we can show the benefits of our modified ILO and the newinitialization schemes. Additionally, we analyze the performance of ourapproach on the Gaussian phase retrieval problem.

Optimizing Intermediate Representations of Generative Models for Phase Retrieval