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

Implicit neural representations such as Neural Radiance Field (NeRF) havefocused mainly on modeling static objects captured under multi-view settingswhere real-time rendering can be achieved with smart data structures, e.g.,PlenOctree. In this paper, we present a novel Fourier PlenOctree (FPO)technique to tackle efficient neural modeling and real-time rendering ofdynamic scenes captured under the free-view video (FVV) setting. The key ideain our FPO is a novel combination of generalized NeRF, PlenOctreerepresentation, volumetric fusion and Fourier transform. To accelerate FPOconstruction, we present a novel coarse-to-fine fusion scheme that leveragesthe generalizable NeRF technique to generate the tree via spatial blending. Totackle dynamic scenes, we tailor the implicit network to model the Fouriercoefficients of timevarying density and color attributes. Finally, we constructthe FPO and train the Fourier coefficients directly on the leaves of a unionPlenOctree structure of the dynamic sequence. We show that the resulting FPOenables compact memory overload to handle dynamic objects and supportsefficient fine-tuning. Extensive experiments show that the proposed method is3000 times faster than the original NeRF and achieves over an order ofmagnitude acceleration over SOTA while preserving high visual quality for thefree-viewpoint rendering of unseen dynamic scenes.

Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-time