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

We present a novel up-resing technique for generating high-resolution liquidsbased on scene flow estimation using deep neural networks. Our approach infersand synthesizes small- and large-scale details solely from a low-resolutionparticle-based liquid simulation. The proposed network leverages neighborhoodcontributions to encode inherent liquid properties throughout convolutions. Wealso propose a particle-based approach to interpolate between liquids generatedfrom varying simulation discretizations using a state-of-the-art bidirectionaloptical flow solver method for fluids in addition to a novel key-eventtopological alignment constraint. In conjunction with the neighborhoodcontributions, our loss formulation allows the inference model throughoutepochs to reward important differences in regard to significant gaps insimulation discretizations. Even when applied in an untested simulation setup,our approach is able to generate plausible high-resolution details. Using thisinterpolation approach and the predicted displacements, our approach combinesthe input liquid properties with the predicted motion to infer semi-Lagrangianadvection. We furthermore showcase how the proposed interpolation approach canfacilitate generating large simulation datasets with a subset of initialcondition parameters.

Neural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquids