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

A crucial reason for the success of existing NeRF-based methods is to build aneural density field for the geometry representation via multiple perceptronlayers (MLPs). MLPs are continuous functions, however, real geometry or densityfield is frequently discontinuous at the interface between the air and thesurface. Such a contrary brings the problem of unfaithful geometryrepresentation. To this end, this paper proposes spiking NeRF, which leveragesspiking neurons and a hybrid Artificial Neural Network (ANN)-Spiking NeuralNetwork (SNN) framework to build a discontinuous density field for faithfulgeometry representation. Specifically, we first demonstrate the reason whycontinuous density fields will bring inaccuracy. Then, we propose to use thespiking neurons to build a discontinuous density field. We conduct acomprehensive analysis for the problem of existing spiking neuron models andthen provide the numerical relationship between the parameter of the spikingneuron and the theoretical accuracy of geometry. Based on this, we propose abounded spiking neuron to build the discontinuous density field. Our methodachieves SOTA performance. The source code and the supplementary material areavailable at https://github.com/liaozhanfeng/Spiking-NeRF.

Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation