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

Image and video restoration has achieved a remarkable leap with the advent ofdeep learning. The success of deep learning paradigm lies in three keycomponents: data, model, and loss. Currently, many efforts have been devoted tothe first two while seldom study focuses on loss function. With the question``are the de facto optimization functions e.g., $L_1$, $L_2$, and perceptuallosses optimal?'', we explore the potential of loss and raise our belief``learned loss function empowers the learning capability of neural networks forimage and video restoration''.  Concretely, we stand on the shoulders of the masked Autoencoders (MAE) andformulate it as a `learned loss function', owing to the fact the pre-trainedMAE innately inherits the prior of image reasoning. We investigate the efficacyof our belief from three perspectives: 1) from task-customized MAE to nativeMAE, 2) from image task to video task, and 3) from transformer structure toconvolution neural network structure. Extensive experiments across multipleimage and video tasks, including image denoising, image super-resolution, imageenhancement, guided image super-resolution, video denoising, and videoenhancement, demonstrate the consistent performance improvements introduced bythe learned loss function. Besides, the learned loss function is preferable asit can be directly plugged into existing networks during training withoutinvolving computations in the inference stage. Code will be publicly available.

Unlocking Masked Autoencoders as Loss Function for Image and Video Restoration