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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Reconstruction tasks in computer vision aim fundamentally to recover anundetermined signal from a set of noisy measurements. Examples includesuper-resolution, image denoising, and non-rigid structure from motion, all ofwhich have seen recent advancements through deep learning. However, earlierwork made extensive use of sparse signal reconstruction frameworks (e.gconvolutional sparse coding). While this work was ultimately surpassed by deeplearning, it rested on a much more developed theoretical framework. Recent workby Papyan et. al provides a bridge between the two approaches by showing how aconvolutional neural network (CNN) can be viewed as an approximate solution toa convolutional sparse coding (CSC) problem. In this work we argue that forsome types of inverse problems the CNN approximation breaks down leading topoor performance. We argue that for these types of problems the CSC approachshould be used instead and validate this argument with empirical evidence.Specifically we identify JPEG artifact reduction and non-rigid trajectoryreconstruction as challenging inverse problems for CNNs and demonstrate stateof the art performance on them using a CSC method. Furthermore, we offer somepractical improvements to this model and its application, and also show howinsights from the CSC model can be used to make CNNs effective in tasks wheretheir naive application fails.

When to Use Convolutional Neural Networks for Inverse Problems