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

Since their introduction, Neural Fields have become very popular for 3Dreconstruction and new view synthesis. Recent researches focused onaccelerating the process, as well as improving the robustness to variation ofthe observation distance and limited number of supervised viewpoints. However,those approaches often led to dedicated solutions that cannot be easilycombined. To tackle this issue, we introduce a new simple but efficientarchitecture named RING-NeRF, based on Residual Implicit Neural Grids, thatprovides a control on the level of detail of the mapping function between thescene and the latent spaces. Associated with a distance-aware forward mappingmechanism and a continuous coarse-to-fine reconstruction process, our versatilearchitecture demonstrates both fast training and state-of-the-art performancesin terms of: (1) anti-aliased rendering, (2) reconstruction quality from fewsupervised viewpoints, and (3) robustness in the absence of appropriatescene-specific initialization for SDF-based NeRFs. We also demonstrate that ourarchitecture can dynamically add grids to increase the details of thereconstruction, opening the way to adaptive reconstruction.

RING-NeRF: A Versatile Architecture based on Residual Implicit Neural Grids