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

Neural Radiance Field (NeRF) has broken new ground in the novel viewsynthesis due to its simple concept and state-of-the-art quality. However, itsuffers from severe performance degradation unless trained with a dense set ofimages with different camera poses, which hinders its practical applications.Although previous methods addressing this problem achieved promising results,they relied heavily on the additional training resources, which goes againstthe philosophy of sparse-input novel-view synthesis pursuing the trainingefficiency. In this work, we propose MixNeRF, an effective training strategyfor novel view synthesis from sparse inputs by modeling a ray with a mixturedensity model. Our MixNeRF estimates the joint distribution of RGB colors alongthe ray samples by modeling it with mixture of distributions. We also propose anew task of ray depth estimation as a useful training objective, which ishighly correlated with 3D scene geometry. Moreover, we remodel the colors withregenerated blending weights based on the estimated ray depth and furtherimproves the robustness for colors and viewpoints. Our MixNeRF outperformsother state-of-the-art methods in various standard benchmarks with superiorefficiency of training and inference.

MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputs