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

Motion-based video frame interpolation commonly relies on optical flow towarp pixels from the inputs to the desired interpolation instant. Yet due tothe inherent challenges of motion estimation (e.g. occlusions anddiscontinuities), most state-of-the-art interpolation approaches requiresubsequent refinement of the warped result to generate satisfying outputs,which drastically decreases the efficiency for multi-frame interpolation. Inthis work, we propose a fully differentiable Many-to-Many (M2M) splattingframework to interpolate frames efficiently. Specifically, given a frame pair,we estimate multiple bidirectional flows to directly forward warp the pixels tothe desired time step, and then fuse any overlapping pixels. In doing so, eachsource pixel renders multiple target pixels and each target pixel can besynthesized from a larger area of visual context. This establishes amany-to-many splatting scheme with robustness to artifacts like holes.Moreover, for each input frame pair, M2M only performs motion estimation onceand has a minuscule computational overhead when interpolating an arbitrarynumber of in-between frames, hence achieving fast multi-frame interpolation. Weconducted extensive experiments to analyze M2M, and found that it significantlyimproves efficiency while maintaining high effectiveness.

Many-to-many Splatting for Efficient Video Frame Interpolation