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 fields (NeRF) show great success in novel view synthesis.However, in real-world scenes, recovering high-quality details from the sourceimages is still challenging for the existing NeRF-based approaches, due to thepotential imperfect calibration information and scene representationinaccuracy. Even with high-quality training frames, the synthetic novel viewsproduced by NeRF models still suffer from notable rendering artifacts, such asnoise, blur, etc. Towards to improve the synthesis quality of NeRF-basedapproaches, we propose NeRFLiX, a general NeRF-agnostic restorer paradigm bylearning a degradation-driven inter-viewpoint mixer. Specially, we design aNeRF-style degradation modeling approach and construct large-scale trainingdata, enabling the possibility of effectively removing NeRF-native renderingartifacts for existing deep neural networks. Moreover, beyond the degradationremoval, we propose an inter-viewpoint aggregation framework that is able tofuse highly related high-quality training images, pushing the performance ofcutting-edge NeRF models to entirely new levels and producing highlyphoto-realistic synthetic views.

NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer