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 tackle the problem of dense light field (LF) reconstructionfrom sparsely-sampled ones with wide baselines and propose a learnable model,namely dynamic interpolation, to replace the commonly-used geometry warpingoperation. Specifically, with the estimated geometric relation between inputviews, we first construct a lightweight neural network to dynamically learnweights for interpolating neighbouring pixels from input views to synthesizeeach pixel of novel views independently. In contrast to the fixed andcontent-independent weights employed in the geometry warping operation, thelearned interpolation weights implicitly incorporate the correspondencesbetween the source and novel views and adapt to different image contentinformation. Then, we recover the spatial correlation between the independentlysynthesized pixels of each novel view by referring to that of input views usinga geometry-based spatial refinement module. We also constrain the angularcorrelation between the novel views through a disparity-oriented LF structureloss. Experimental results on LF datasets with wide baselines show that thereconstructed LFs achieve much higher PSNR/SSIM and preserve the LF parallaxstructure better than state-of-the-art methods. The source code is publiclyavailable at https://github.com/MantangGuo/DI4SLF.

Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines