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

Each photo in an image burst can be considered a sample of a complex 3Dscene: the product of parallax, diffuse and specular materials, scene motion,and illuminant variation. While decomposing all of these effects from a stackof misaligned images is a highly ill-conditioned task, the conventionalalign-and-merge burst pipeline takes the other extreme: blending them into asingle image. In this work, we propose a versatile intermediate representation:a two-layer alpha-composited image plus flow model constructed with neuralspline fields -- networks trained to map input coordinates to spline controlpoints. Our method is able to, during test-time optimization, jointly fuse aburst image capture into one high-resolution reconstruction and decompose itinto transmission and obstruction layers. Then, by discarding the obstructionlayer, we can perform a range of tasks including seeing through occlusions,reflection suppression, and shadow removal. Validated on complex synthetic andin-the-wild captures we find that, with no post-processing steps or learnedpriors, our generalizable model is able to outperform existing dedicatedsingle-image and multi-view obstruction removal approaches.

Neural Spline Fields for Burst Image Fusion and Layer Separation