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

In this paper, we propose a learning-based approach for denoising raw videoscaptured under low lighting conditions. We propose to do this by firstexplicitly aligning the neighboring frames to the current frame using aconvolutional neural network (CNN). We then fuse the registered frames usinganother CNN to obtain the final denoised frame. To avoid directly aligning thetemporally distant frames, we perform the two processes of alignment and fusionin multiple stages. Specifically, at each stage, we perform the denoisingprocess on three consecutive input frames to generate the intermediate denoisedframes which are then passed as the input to the next stage. By performing theprocess in multiple stages, we can effectively utilize the information ofneighboring frames without directly aligning the temporally distant frames. Wetrain our multi-stage system using an adversarial loss with a conditionaldiscriminator. Specifically, we condition the discriminator on a soft gradientmask to prevent introducing high-frequency artifacts in smooth regions. We showthat our system is able to produce temporally coherent videos with realisticdetails. Furthermore, we demonstrate through extensive experiments that ourapproach outperforms state-of-the-art image and video denoising methods bothnumerically and visually.

Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask